{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/inference-attack/papers/2","list_of":"/task/inference-attack","task":"Inference Attack","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":2,"pages_in_order":3,"rows_per_page":100,"rows":[101,200],"of":283,"counts":{"archive_papers_tagged":283,"with_a_code_link":114,"where_syntology_ran_a_sample":48,"not_listed_spam_title":0,"listed":283,"listed_where_code_ran":48,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":30,"every_run_a_failure_of_syntologys_instrument":18,"listed_with_a_run_with_no_instrument_failure":30,"listed_every_run_a_failure_of_syntologys_instrument":18,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/inference-attack","prev":"/task/inference-attack","next":"/task/inference-attack/papers/3","papers":[{"url":"/paper/revisiting-membership-inference-under","slug":"revisiting-membership-inference-under","title":"Revisiting Membership Inference Under Realistic Assumptions","date":"2020-05-21","arxiv_id":"2005.10881","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/revisiting-membership-inference-under#ran","syntology_url":"https://syntology.ai/paper/2005.10881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.10881"}},"official":{"repos":["bargavj/EvaluatingDPML"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/when-machine-unlearning-jeopardizes-privacy","slug":"when-machine-unlearning-jeopardizes-privacy","title":"When Machine Unlearning Jeopardizes Privacy","date":"2020-05-05","arxiv_id":"2005.02205","repositories_listed":1,"syntology":null},{"url":"/paper/exploiting-defenses-against-gan-based-feature","slug":"exploiting-defenses-against-gan-based-feature","title":"Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning","date":"2020-04-27","arxiv_id":"2004.12571","repositories_listed":1,"syntology":null},{"url":"/paper/systematic-evaluation-of-privacy-risks-of","slug":"systematic-evaluation-of-privacy-risks-of","title":"Systematic Evaluation of Privacy Risks of Machine Learning Models","date":"2020-03-24","arxiv_id":"2003.10595","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/systematic-evaluation-of-privacy-risks-of#ran","syntology_url":"https://syntology.ai/paper/2003.10595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.10595"}},"official":{"repos":["inspire-group/membership-inference-evaluation"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/data-and-model-dependencies-of-membership","slug":"data-and-model-dependencies-of-membership","title":"Data and Model Dependencies of Membership Inference Attack","date":"2020-02-17","arxiv_id":"2002.06856","repositories_listed":1,"syntology":null},{"url":"/paper/membership-inference-attacks-against-object","slug":"membership-inference-attacks-against-object","title":"Membership Inference Attacks Against Object Detection Models","date":"2020-01-12","arxiv_id":"2001.04011","repositories_listed":1,"syntology":null},{"url":"/paper/assessing-differentially-private-deep","slug":"assessing-differentially-private-deep","title":"Assessing differentially private deep learning with Membership Inference","date":"2019-12-24","arxiv_id":"1912.11328","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/assessing-differentially-private-deep#ran","syntology_url":"https://syntology.ai/paper/1912.11328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.11328"}},"official":{"repos":["SAP-samples/security-research-membership-inference-and-differential-privacy"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-intrinsic-privacy-of-stochastic","slug":"on-the-intrinsic-privacy-of-stochastic","title":"An Empirical Study on the Intrinsic Privacy of SGD","date":"2019-12-05","arxiv_id":"1912.02919","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/on-the-intrinsic-privacy-of-stochastic#ran","syntology_url":"https://syntology.ai/paper/1912.02919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.02919"}},"official":{"repos":["microsoft/intrinsic-private-sgd"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/robust-and-undetectable-white-box-watermarks","slug":"robust-and-undetectable-white-box-watermarks","title":"RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks","date":"2019-10-31","arxiv_id":"1910.14268","repositories_listed":1,"syntology":null},{"url":"/paper/gan-leaks-a-taxonomy-of-membership-inference","slug":"gan-leaks-a-taxonomy-of-membership-inference","title":"GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models","date":"2019-09-09","arxiv_id":"1909.03935","repositories_listed":1,"syntology":{"n":22,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":9,"n_honours":3,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/gan-leaks-a-taxonomy-of-membership-inference#ran","syntology_url":"https://syntology.ai/paper/1909.03935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03935"}},"official":{"repos":["DingfanChen/GAN-Leaks"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/reconstruction-and-membership-inference","slug":"reconstruction-and-membership-inference","title":"Reconstruction and Membership Inference Attacks against Generative Models","date":"2019-06-07","arxiv_id":"1906.03006","repositories_listed":1,"syntology":null},{"url":"/paper/privacy-risks-of-securing-machine-learning","slug":"privacy-risks-of-securing-machine-learning","title":"Privacy Risks of Securing Machine Learning Models against Adversarial Examples","date":"2019-05-24","arxiv_id":"1905.10291","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/privacy-risks-of-securing-machine-learning#ran","syntology_url":"https://syntology.ai/paper/1905.10291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10291"}},"official":{"repos":["inspire-group/privacy-vs-robustness"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/machine-learning-with-membership-privacy","slug":"machine-learning-with-membership-privacy","title":"Machine Learning with Membership Privacy using Adversarial Regularization","date":"2018-07-16","arxiv_id":"1807.05852","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-membership-inferences-on-well","slug":"understanding-membership-inferences-on-well","title":"Understanding Membership Inferences on Well-Generalized Learning Models","date":"2018-02-13","arxiv_id":"1802.04889","repositories_listed":1,"syntology":null},{"url":null,"slug":"orthogonal-soft-pruning-for-efficient-class","title":"Orthogonal Soft Pruning for Efficient Class Unlearning","date":"2025-06-24","arxiv_id":"2506.19891","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-better-features-mean-greater-risks-the","title":"When Better Features Mean Greater Risks: The Performance-Privacy Trade-Off in Contrastive Learning","date":"2025-06-06","arxiv_id":"2506.05743","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attacks-on-sequence","title":"Membership Inference Attacks on Sequence Models","date":"2025-06-05","arxiv_id":"2506.05126","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-out-of-distribution-membership-inference","title":"An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks","date":"2025-05-26","arxiv_id":"2505.20074","repositories_listed":0,"syntology":null},{"url":null,"slug":"ec-lda-label-distribution-inference-attack","title":"EC-LDA : Label Distribution Inference Attack against Federated Graph Learning with Embedding Compression","date":"2025-05-21","arxiv_id":"2505.15140","repositories_listed":0,"syntology":null},{"url":null,"slug":"securing-genomic-data-against-inference","title":"Securing Genomic Data Against Inference Attacks in Federated Learning Environments","date":"2025-05-12","arxiv_id":"2505.07188","repositories_listed":0,"syntology":null},{"url":null,"slug":"augmixcloak-a-defense-against-membership","title":"AugMixCloak: A Defense against Membership Inference Attacks via Image Transformation","date":"2025-05-11","arxiv_id":"2505.07149","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-new-membership-inference-attack-that-spots","title":"A new membership inference attack that spots memorization in generative and predictive models: Loss-Based with Reference Model algorithm (LBRM)","date":"2025-05-06","arxiv_id":"2505.03490","repositories_listed":0,"syntology":null},{"url":null,"slug":"whispers-of-data-unveiling-label","title":"Whispers of Data: Unveiling Label Distributions in Federated Learning Through Virtual Client Simulation","date":"2025-04-30","arxiv_id":"2504.21436","repositories_listed":0,"syntology":null},{"url":null,"slug":"desia-attribute-inference-attacks-against","title":"DeSIA: Attribute Inference Attacks Against Limited Fixed Aggregate Statistics","date":"2025-04-25","arxiv_id":"2504.18497","repositories_listed":0,"syntology":null},{"url":null,"slug":"disparate-privacy-vulnerability-targeted","title":"Disparate Privacy Vulnerability: Targeted Attribute Inference Attacks and Defenses","date":"2025-04-05","arxiv_id":"2504.04033","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-level-label-only-membership-inference","title":"Graph-Level Label-Only Membership Inference Attack against Graph Neural Networks","date":"2025-03-24","arxiv_id":"2503.19070","repositories_listed":0,"syntology":null},{"url":null,"slug":"blia-detect-model-memorization-in-binary","title":"BLIA: Detect model memorization in binary classification model through passive Label Inference attack","date":"2025-03-17","arxiv_id":"2503.12801","repositories_listed":0,"syntology":null},{"url":null,"slug":"dp-gpl-differentially-private-graph-prompt","title":"DP-GPL: Differentially Private Graph Prompt Learning","date":"2025-03-13","arxiv_id":"2503.10544","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-membership-inference-attacks-by","title":"Efficient Membership Inference Attacks by Bayesian Neural Network","date":"2025-03-10","arxiv_id":"2503.07482","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-label-only-membership-inference","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","date":"2025-02-26","arxiv_id":"2502.18943","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attacks-for-face-images","title":"Membership Inference Attacks for Face Images Against Fine-Tuned Latent Diffusion Models","date":"2025-02-17","arxiv_id":"2502.11619","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-hierarchical-approach-for-assessing-the","title":"A hierarchical approach for assessing the vulnerability of tree-based classification models to membership inference attack","date":"2025-02-13","arxiv_id":"2502.09396","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-client-privacy-leakage-from-public","title":"Unveiling Client Privacy Leakage from Public Dataset Usage in Federated Distillation","date":"2025-02-11","arxiv_id":"2502.08001","repositories_listed":0,"syntology":null},{"url":null,"slug":"metric-privacy-in-federated-learning-for","title":"Metric Privacy in Federated Learning for Medical Imaging: Improving Convergence and Preventing Client Inference Attacks","date":"2025-02-03","arxiv_id":"2502.01352","repositories_listed":0,"syntology":null},{"url":null,"slug":"tool-unlearning-for-tool-augmented-llms","title":"Tool Unlearning for Tool-Augmented LLMs","date":"2025-02-03","arxiv_id":"2502.01083","repositories_listed":0,"syntology":null},{"url":"/paper/redefining-machine-unlearning-a-conformal","slug":"redefining-machine-unlearning-a-conformal","title":"Redefining Machine Unlearning: A Conformal Prediction-Motivated Approach","date":"2025-01-31","arxiv_id":"2501.19403","repositories_listed":0,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/redefining-machine-unlearning-a-conformal#ran","syntology_url":"https://syntology.ai/paper/2501.19403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19403"}},"official":null}},{"url":null,"slug":"unlearning-clients-features-and-samples-in","title":"Unlearning Clients, Features and Samples in Vertical Federated Learning","date":"2025-01-23","arxiv_id":"2501.13683","repositories_listed":0,"syntology":null},{"url":null,"slug":"tag-tab-pretraining-data-detection-in-large","title":"Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack","date":"2025-01-14","arxiv_id":"2501.08454","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-volumetric-approach-to-privacy-of-dynamical","title":"A Volumetric Approach to Privacy of Dynamical Systems","date":"2025-01-06","arxiv_id":"2501.02893","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-models-to-network-topologies-a-topology","title":"From Models to Network Topologies: A Topology Inference Attack in Decentralized Federated Learning","date":"2025-01-06","arxiv_id":"2501.03119","repositories_listed":0,"syntology":null},{"url":null,"slug":"adamixup-a-dynamic-defense-framework-for","title":"AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation","date":"2025-01-04","arxiv_id":"2501.02182","repositories_listed":0,"syntology":null},{"url":null,"slug":"prompt-based-unifying-inference-attack-on","title":"Prompt-based Unifying Inference Attack on Graph Neural Networks","date":"2024-12-20","arxiv_id":"2412.15735","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-statistical-and-multi-perspective","title":"A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models","date":"2024-12-18","arxiv_id":"2412.13475","repositories_listed":0,"syntology":null},{"url":null,"slug":"effectiveness-of-l2-regularization-in-privacy","title":"Effectiveness of L2 Regularization in Privacy-Preserving Machine Learning","date":"2024-12-02","arxiv_id":"2412.01541","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attack-against-long","title":"Membership Inference Attack against Long-Context Large Language Models","date":"2024-11-18","arxiv_id":"2411.11424","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-privacy-risk-of-in-context-learning","title":"On the Privacy Risk of In-context Learning","date":"2024-11-15","arxiv_id":"2411.10512","repositories_listed":0,"syntology":null},{"url":"/paper/tddbench-a-benchmark-for-training-data","slug":"tddbench-a-benchmark-for-training-data","title":"TDDBench: A Benchmark for Training data detection","date":"2024-11-05","arxiv_id":"2411.03363","repositories_listed":0,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tddbench-a-benchmark-for-training-data#ran","syntology_url":"https://syntology.ai/paper/2411.03363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.03363"}},"official":null}},{"url":null,"slug":"waka-data-attribution-using-k-nearest","title":"WaKA: Data Attribution using K-Nearest Neighbors and Membership Privacy Principles","date":"2024-11-02","arxiv_id":"2411.01357","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-synthetic-faces-how-synthetic","title":"Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities","date":"2024-10-31","arxiv_id":"2410.24015","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-dynamic-assortment","title":"Privacy-Preserving Dynamic Assortment Selection","date":"2024-10-29","arxiv_id":"2410.22488","repositories_listed":0,"syntology":null},{"url":null,"slug":"identity-focused-inference-and-extraction","title":"Identity-Focused Inference and Extraction Attacks on Diffusion Models","date":"2024-10-14","arxiv_id":"2410.10177","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-vulnerabilities-in-marginals-based","title":"Privacy Vulnerabilities in Marginals-based Synthetic Data","date":"2024-10-07","arxiv_id":"2410.05506","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-privacy-evaluation-in-deep-spiking","title":"Membership Privacy Evaluation in Deep Spiking Neural Networks","date":"2024-09-28","arxiv_id":"2409.19413","repositories_listed":0,"syntology":null},{"url":null,"slug":"subject-data-auditing-via-source-inference","title":"Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learning","date":"2024-09-28","arxiv_id":"2409.19417","repositories_listed":0,"syntology":null},{"url":null,"slug":"gazeploit-remote-keystroke-inference-attack","title":"GAZEploit: Remote Keystroke Inference Attack by Gaze Estimation from Avatar Views in VR/MR Devices","date":"2024-09-12","arxiv_id":"2409.08122","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attacks-against-in","title":"Membership Inference Attacks Against In-Context Learning","date":"2024-09-02","arxiv_id":"2409.01380","repositories_listed":0,"syntology":null},{"url":null,"slug":"membership-inference-attack-against-masked","title":"Membership Inference Attack Against Masked Image Modeling","date":"2024-08-13","arxiv_id":"2408.06825","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00722","title":"Pathway to Secure and Trustworthy ZSM for LLMs: Attacks, Defense, and Opportunities","date":"2024-08-01","arxiv_id":"2408.00722","repositories_listed":0,"syntology":null},{"url":null,"slug":"accuracy-privacy-trade-off-in-the-mitigation","title":"Accuracy-Privacy Trade-off in the Mitigation of Membership Inference Attack in Federated Learning","date":"2024-07-26","arxiv_id":"2407.19119","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-privacy-vulnerabilities","title":"Unveiling Privacy Vulnerabilities: Investigating the Role of Structure in Graph Data","date":"2024-07-26","arxiv_id":"2407.18564","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-structural-memorization-structural","title":"Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models","date":"2024-07-18","arxiv_id":"2407.13252","repositories_listed":0,"syntology":null},{"url":null,"slug":"feature-inference-attack-on-shapley-values","title":"Feature Inference Attack on Shapley Values","date":"2024-07-16","arxiv_id":"2407.11359","repositories_listed":0,"syntology":null},{"url":null,"slug":"exposing-privacy-gaps-membership-inference","title":"Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment","date":"2024-07-08","arxiv_id":"2407.06443","repositories_listed":0,"syntology":null},{"url":null,"slug":"curvature-clues-decoding-deep-learning","title":"Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature","date":"2024-07-03","arxiv_id":"2407.02747","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-zero-auxiliary-knowledge-membership","title":"A Zero Auxiliary Knowledge Membership Inference Attack on Aggregate Location Data","date":"2024-06-26","arxiv_id":"2406.18671","repositories_listed":0,"syntology":null},{"url":null,"slug":"recall-membership-inference-via-relative","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","date":"2024-06-23","arxiv_id":"2406.15968","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-secure-aggregation-label-leakage","title":"Breaking Secure Aggregation: Label Leakage from Aggregated Gradients in Federated Learning","date":"2024-06-22","arxiv_id":"2406.15731","repositories_listed":0,"syntology":null},{"url":null,"slug":"fingerprint-membership-and-identity-inference","title":"Fingerprint Membership and Identity Inference Against Generative Adversarial Networks","date":"2024-06-21","arxiv_id":"2406.15253","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-plagiarism-index-characterizing-the","title":"Data Plagiarism Index: Characterizing the Privacy Risk of Data-Copying in Tabular Generative Models","date":"2024-06-18","arxiv_id":"2406.13012","repositories_listed":0,"syntology":null},{"url":null,"slug":"semantic-membership-inference-attack-against","title":"Semantic Membership Inference Attack against Large Language Models","date":"2024-06-14","arxiv_id":"2406.10218","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-unlearning-for-uplink-interference","title":"Machine Unlearning for Uplink Interference Cancellation","date":"2024-06-10","arxiv_id":"2406.05945","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-attacks-in-machine-learning-as-a","title":"Inference Attacks: A Taxonomy, Survey, and Promising Directions","date":"2024-06-04","arxiv_id":"2406.02027","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-my-data-in-your-retrieval-database","title":"Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation","date":"2024-05-30","arxiv_id":"2405.20446","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-black-box-membership-inference-attack","title":"Towards Black-Box Membership Inference Attack for Diffusion Models","date":"2024-05-25","arxiv_id":"2405.20771","repositories_listed":0,"syntology":null},{"url":null,"slug":"many-shot-regurgitation-msr-prompting","title":"Many-Shot Regurgitation (MSR) Prompting","date":"2024-05-13","arxiv_id":"2405.08134","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-graph-condensation-with-information","title":"Federated Graph Condensation with Information Bottleneck Principles","date":"2024-05-07","arxiv_id":"2405.03911","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-reliable-empirical-machine-unlearning","title":"Towards Reliable Empirical Machine Unlearning Evaluation: A Game-Theoretic View","date":"2024-04-17","arxiv_id":"2404.11577","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperparameter-optimization-for-secureboost","title":"Hyperparameter Optimization for SecureBoost via Constrained Multi-Objective Federated Learning","date":"2024-04-06","arxiv_id":"2404.04490","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-federated-parameter-aggregation-method-for","title":"A Federated Parameter Aggregation Method for Node Classification Tasks with Different Graph Network Structures","date":"2024-03-24","arxiv_id":"2403.16004","repositories_listed":0,"syntology":null},{"url":null,"slug":"nabla-t-gradient-based-and-task-agnostic","title":"$\\nabla τ$: Gradient-based and Task-Agnostic machine Unlearning","date":"2024-03-21","arxiv_id":"2403.14339","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-cost-privacy-aware-decentralized-learning","title":"Low-Cost Privacy-Preserving Decentralized Learning","date":"2024-03-18","arxiv_id":"2403.11795","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-calibration-and-membership","title":"On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks","date":"2024-02-16","arxiv_id":"2402.10686","repositories_listed":0,"syntology":null},{"url":null,"slug":"why-does-differential-privacy-with-large","title":"Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?","date":"2024-02-14","arxiv_id":"2402.09540","repositories_listed":0,"syntology":null},{"url":null,"slug":"understanding-practical-membership-privacy-of","title":"Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning","date":"2024-02-07","arxiv_id":"2402.06674","repositories_listed":0,"syntology":null},{"url":null,"slug":"de-identification-is-not-always-enough","title":"De-identification is not always enough","date":"2024-01-31","arxiv_id":"2402.00179","repositories_listed":0,"syntology":null},{"url":null,"slug":"physical-trajectory-inference-attack-and","title":"Physical Trajectory Inference Attack and Defense in Decentralized POI Recommendation","date":"2024-01-26","arxiv_id":"2401.14583","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-attacks-against-face-recognition","title":"Inference Attacks Against Face Recognition Model without Classification Layers","date":"2024-01-24","arxiv_id":"2401.13719","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-and-adversarially","title":"Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation","date":"2024-01-18","arxiv_id":"2401.10405","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-contamination-language-models-may-not-be","title":"Task Contamination: Language Models May Not Be Few-Shot Anymore","date":"2023-12-26","arxiv_id":"2312.16337","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaptive-domain-inference-attack","title":"Adaptive Domain Inference Attack with Concept Hierarchy","date":"2023-12-22","arxiv_id":"2312.15088","repositories_listed":0,"syntology":null},{"url":null,"slug":"poincare-differential-privacy-for-hierarchy","title":"Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding","date":"2023-12-19","arxiv_id":"2312.12183","repositories_listed":0,"syntology":null},{"url":null,"slug":"preserving-privacy-in-gans-against-membership","title":"Preserving Privacy in GANs Against Membership Inference Attack","date":"2023-11-06","arxiv_id":"2311.03172","repositories_listed":0,"syntology":null},{"url":null,"slug":"black-box-training-data-identification-in","title":"Black-Box Training Data Identification in GANs via Detector Networks","date":"2023-10-18","arxiv_id":"2310.12063","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-study-of-privacy-risks-in","title":"A Comprehensive Study of Privacy Risks in Curriculum Learning","date":"2023-10-16","arxiv_id":"2310.10124","repositories_listed":0,"syntology":null},{"url":"/paper/vertexserum-poisoning-graph-neural-networks","slug":"vertexserum-poisoning-graph-neural-networks","title":"VertexSerum: Poisoning Graph Neural Networks for Link Inference","date":"2023-08-02","arxiv_id":"2308.01469","repositories_listed":0,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vertexserum-poisoning-graph-neural-networks#ran","syntology_url":"https://syntology.ai/paper/2308.01469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.01469"}},"official":null}},{"url":null,"slug":"epsilon-privacy-metric-for-machine-learning","title":"Epsilon*: Privacy Metric for Machine Learning Models","date":"2023-07-21","arxiv_id":"2307.11280","repositories_listed":0,"syntology":null},{"url":null,"slug":"eliminating-label-leakage-in-tree-based","title":"Eliminating Label Leakage in Tree-Based Vertical Federated Learning","date":"2023-07-19","arxiv_id":"2307.10318","repositories_listed":0,"syntology":null},{"url":null,"slug":"set-membership-inference-attacks-using-data","title":"Set-Membership Inference Attacks using Data Watermarking","date":"2023-06-22","arxiv_id":"2307.15067","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-more-realistic-membership-inference","title":"Towards More Realistic Membership Inference Attacks on Large Diffusion Models","date":"2023-06-22","arxiv_id":"2306.12983","repositories_listed":0,"syntology":null},{"url":null,"slug":"community-detection-attack-against","title":"Inferring Communities of Interest in Collaborative Learning-based Recommender Systems","date":"2023-06-15","arxiv_id":"2306.08929","repositories_listed":0,"syntology":null}],"record_sha256":"62fad0ef706db8c80f24e3f141d470aa4d1233a2712f0a960b52ea434e6679cd","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}