{"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/adversarial-attack/papers/10","list_of":"/task/adversarial-attack","task":"Adversarial 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":10,"pages_in_order":19,"rows_per_page":100,"rows":[901,1000],"of":1808,"counts":{"archive_papers_tagged":1808,"with_a_code_link":745,"where_syntology_ran_a_sample":206,"not_listed_spam_title":0,"listed":1808,"listed_where_code_ran":206,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":161,"every_run_a_failure_of_syntologys_instrument":45,"listed_with_a_run_with_no_instrument_failure":161,"listed_every_run_a_failure_of_syntologys_instrument":45,"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/adversarial-attack","prev":"/task/adversarial-attack/papers/9","next":"/task/adversarial-attack/papers/11","papers":[{"url":null,"slug":"golden-ratio-search-a-low-power-adversarial","title":"Golden Ratio Search: A Low-Power Adversarial Attack for Deep Learning based Modulation Classification","date":"2024-09-17","arxiv_id":"2409.11454","repositories_listed":0,"syntology":null},{"url":null,"slug":"revisiting-physical-world-adversarial-attack","title":"Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective","date":"2024-09-15","arxiv_id":"2409.09860","repositories_listed":0,"syntology":null},{"url":null,"slug":"xsub-explanation-driven-adversarial-attack","title":"XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution","date":"2024-09-13","arxiv_id":"2409.08919","repositories_listed":0,"syntology":null},{"url":null,"slug":"d-captcha-a-study-of-resilience-of-deepfake","title":"D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attack","date":"2024-09-11","arxiv_id":"2409.07390","repositories_listed":0,"syntology":null},{"url":null,"slug":"unrevealed-threats-a-comprehensive-study-of","title":"Unrevealed Threats: A Comprehensive Study of the Adversarial Robustness of Underwater Image Enhancement Models","date":"2024-09-10","arxiv_id":"2409.06420","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlearning-or-concealment-a-critical-analysis","title":"Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models","date":"2024-09-09","arxiv_id":"2409.05668","repositories_listed":0,"syntology":null},{"url":null,"slug":"openfact-at-checkthat-2024-combining-multiple","title":"OpenFact at CheckThat! 2024: Combining Multiple Attack Methods for Effective Adversarial Text Generation","date":"2024-09-04","arxiv_id":"2409.02649","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-index-vector-quantization-based","title":"One-Index Vector Quantization Based Adversarial Attack on Image Classification","date":"2024-09-02","arxiv_id":"2409.01282","repositories_listed":0,"syntology":null},{"url":null,"slug":"tf-attack-transferable-and-fast-adversarial","title":"TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models","date":"2024-08-26","arxiv_id":"2408.13985","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-the-robustness-of-vision-language","title":"Probing the Robustness of Vision-Language Pretrained Models: A Multimodal Adversarial Attack Approach","date":"2024-08-24","arxiv_id":"2408.13461","repositories_listed":0,"syntology":null},{"url":null,"slug":"banktweak-adversarial-attack-against-multi","title":"BankTweak: Adversarial Attack against Multi-Object Trackers by Manipulating Feature Banks","date":"2024-08-22","arxiv_id":"2408.12727","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-transferability-of-adversarial","title":"Enhancing Transferability of Adversarial Attacks with GE-AdvGAN+: A Comprehensive Framework for Gradient Editing","date":"2024-08-22","arxiv_id":"2408.12673","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-efficient-video-adversarial-attack-with","title":"Query-Efficient Video Adversarial Attack with Stylized Logo","date":"2024-08-22","arxiv_id":"2408.12099","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlation-analysis-of-adversarial-attack-in","title":"Correlation Analysis of Adversarial Attack in Time Series Classification","date":"2024-08-21","arxiv_id":"2408.11264","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attack-for-explanation-robustness","title":"Adversarial Attack for Explanation Robustness of Rationalization Models","date":"2024-08-20","arxiv_id":"2408.10795","repositories_listed":0,"syntology":null},{"url":null,"slug":"gaim-attacking-graph-neural-networks-via","title":"GAIM: Attacking Graph Neural Networks via Adversarial Influence Maximization","date":"2024-08-20","arxiv_id":"2408.10948","repositories_listed":0,"syntology":null},{"url":null,"slug":"msmemorygan-a-multi-scale-memory-gan-for-palm","title":"MsMemoryGAN: A Multi-scale Memory GAN for Palm-vein Adversarial Purification","date":"2024-08-20","arxiv_id":"2408.10694","repositories_listed":0,"syntology":null},{"url":null,"slug":"dft-based-adversarial-attack-detection-in-mri","title":"DFT-Based Adversarial Attack Detection in MRI Brain Imaging: Enhancing Diagnostic Accuracy in Alzheimer's Case Studies","date":"2024-08-16","arxiv_id":"2408.08489","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-adversarial-attacks-via-parameter","title":"Enhancing Adversarial Attacks via Parameter Adaptive Adversarial Attack","date":"2024-08-14","arxiv_id":"2408.07733","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-active-learning-roal-countering","title":"Robust Active Learning (RoAL): Countering Dynamic Adversaries in Active Learning with Elastic Weight Consolidation","date":"2024-08-14","arxiv_id":"2408.07364","repositories_listed":0,"syntology":null},{"url":null,"slug":"retome-va-recursive-token-merging-for-video","title":"ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack","date":"2024-08-10","arxiv_id":"2408.05479","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-network-interpretability-via","title":"Improving Network Interpretability via Explanation Consistency Evaluation","date":"2024-08-08","arxiv_id":"2408.04600","repositories_listed":0,"syntology":null},{"url":null,"slug":"simple-perturbations-subvert-ethereum","title":"Simple Perturbations Subvert Ethereum Phishing Transactions Detection: An Empirical Analysis","date":"2024-08-06","arxiv_id":"2408.03441","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00329","title":"OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack","date":"2024-08-01","arxiv_id":"2408.00329","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00348","title":"Securing the Diagnosis of Medical Imaging: An In-depth Analysis of AI-Resistant Attacks","date":"2024-08-01","arxiv_id":"2408.00348","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-llm-enhanced-adversarial-attack","title":"Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion","date":"2024-08-01","arxiv_id":"2408.00352","repositories_listed":0,"syntology":null},{"url":null,"slug":"vulnerabilities-in-ai-generated-image","title":"Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks","date":"2024-07-30","arxiv_id":"2407.20836","repositories_listed":0,"syntology":null},{"url":null,"slug":"physical-adversarial-attack-on-monocular","title":"Physical Adversarial Attack on Monocular Depth Estimation via Shape-Varying Patches","date":"2024-07-24","arxiv_id":"2407.17312","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-dropout-robust-convolutional-neural","title":"Beyond Dropout: Robust Convolutional Neural Networks Based on Local Feature Masking","date":"2024-07-18","arxiv_id":"2407.13646","repositories_listed":0,"syntology":null},{"url":null,"slug":"compressed-models-are-not-miniature-versions","title":"Compressed models are NOT miniature versions of large models","date":"2024-07-18","arxiv_id":"2407.13174","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-task-attack-a-self-supervision","title":"Cross-Task Attack: A Self-Supervision Generative Framework Based on Attention Shift","date":"2024-07-18","arxiv_id":"2407.13700","repositories_listed":0,"syntology":null},{"url":null,"slug":"aemim-adversarial-examples-meet-masked-image","title":"AEMIM: Adversarial Examples Meet Masked Image Modeling","date":"2024-07-16","arxiv_id":"2407.11537","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-tinyml-security-study-of","title":"Enhancing TinyML Security: Study of Adversarial Attack Transferability","date":"2024-07-16","arxiv_id":"2407.11599","repositories_listed":0,"syntology":null},{"url":null,"slug":"wicked-oddities-selectively-poisoning-for","title":"Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks","date":"2024-07-15","arxiv_id":"2407.10825","repositories_listed":0,"syntology":null},{"url":null,"slug":"semiadv-query-efficient-black-box-adversarial","title":"SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images","date":"2024-07-13","arxiv_id":"2407.11073","repositories_listed":0,"syntology":null},{"url":null,"slug":"dlove-a-new-security-evaluation-tool-for-deep","title":"DLOVE: A new Security Evaluation Tool for Deep Learning Based Watermarking Techniques","date":"2024-07-09","arxiv_id":"2407.06552","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-representation-learning-for-13","title":"Self-Supervised Representation Learning for Adversarial Attack Detection","date":"2024-07-05","arxiv_id":"2407.04382","repositories_listed":0,"syntology":null},{"url":null,"slug":"jailbreakhunter-a-visual-analytics-approach","title":"JailbreakHunter: A Visual Analytics Approach for Jailbreak Prompts Discovery from Large-Scale Human-LLM Conversational Datasets","date":"2024-07-03","arxiv_id":"2407.03045","repositories_listed":0,"syntology":null},{"url":null,"slug":"l-p-norm-distortion-efficient-adversarial","title":"$L_p$-norm Distortion-Efficient Adversarial Attack","date":"2024-07-03","arxiv_id":"2407.03115","repositories_listed":0,"syntology":null},{"url":null,"slug":"evolba-evolutionary-boundary-attack-under","title":"EvolBA: Evolutionary Boundary Attack under Hard-label Black Box condition","date":"2024-07-02","arxiv_id":"2407.02248","repositories_listed":0,"syntology":null},{"url":null,"slug":"looking-from-the-future-multi-order","title":"Looking From the Future: Multi-order Iterations Can Enhance Adversarial Attack Transferability","date":"2024-07-02","arxiv_id":"2407.01925","repositories_listed":0,"syntology":null},{"url":null,"slug":"query-efficient-hard-label-black-box-attack-1","title":"Query-Efficient Hard-Label Black-Box Attack against Vision Transformers","date":"2024-06-29","arxiv_id":"2407.00389","repositories_listed":0,"syntology":null},{"url":null,"slug":"deceptive-diffusion-generating-synthetic","title":"Deceptive Diffusion: Generating Synthetic Adversarial Examples","date":"2024-06-28","arxiv_id":"2406.19807","repositories_listed":0,"syntology":null},{"url":null,"slug":"emotion-loss-attacking-adversarial-attack","title":"Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features","date":"2024-06-28","arxiv_id":"2406.19815","repositories_listed":0,"syntology":null},{"url":null,"slug":"idt-dual-task-adversarial-attacks-for-privacy","title":"IDT: Dual-Task Adversarial Attacks for Privacy Protection","date":"2024-06-28","arxiv_id":"2406.19642","repositories_listed":0,"syntology":null},{"url":null,"slug":"cuda2-an-approach-for-incorporating-traitor","title":"CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems","date":"2024-06-25","arxiv_id":"2406.17425","repositories_listed":0,"syntology":null},{"url":null,"slug":"unicad-a-unified-approach-for-attack","title":"UNICAD: A Unified Approach for Attack Detection, Noise Reduction and Novel Class Identification","date":"2024-06-24","arxiv_id":"2406.16501","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effect-of-similarity-measures-on-accurate","title":"The Effect of Similarity Measures on Accurate Stability Estimates for Local Surrogate Models in Text-based Explainable AI","date":"2024-06-22","arxiv_id":"2406.15839","repositories_listed":0,"syntology":null},{"url":null,"slug":"agsoa-graph-neural-network-targeted-attack","title":"AGSOA:Graph Neural Network Targeted Attack Based on Average Gradient and Structure Optimization","date":"2024-06-19","arxiv_id":"2406.13228","repositories_listed":0,"syntology":null},{"url":null,"slug":"graphmu-repairing-robustness-of-graph-neural","title":"GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning","date":"2024-06-19","arxiv_id":"2406.13499","repositories_listed":0,"syntology":null},{"url":null,"slug":"saliency-attention-and-semantic-similarity","title":"Saliency Attention and Semantic Similarity-Driven Adversarial Perturbation","date":"2024-06-18","arxiv_id":"2406.19413","repositories_listed":0,"syntology":null},{"url":null,"slug":"dms-addressing-information-loss-with-more","title":"DMS: Addressing Information Loss with More Steps for Pragmatic Adversarial Attacks","date":"2024-06-09","arxiv_id":"2406.07580","repositories_listed":0,"syntology":null},{"url":null,"slug":"selfdefend-llms-can-defend-themselves-against","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","date":"2024-06-08","arxiv_id":"2406.05498","repositories_listed":0,"syntology":null},{"url":null,"slug":"vqunet-vector-quantization-u-net-for","title":"VQUNet: Vector Quantization U-Net for Defending Adversarial Atacks by Regularizing Unwanted Noise","date":"2024-06-05","arxiv_id":"2406.03117","repositories_listed":0,"syntology":null},{"url":null,"slug":"wavelet-based-image-tokenizer-for-vision","title":"Wavelet-Based Image Tokenizer for Vision Transformers","date":"2024-05-28","arxiv_id":"2405.18616","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-false-sense-of-security-in","title":"Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack","date":"2024-05-25","arxiv_id":"2405.16134","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-measurement-of-deep-learning","title":"Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets","date":"2024-05-25","arxiv_id":"2405.16082","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-on-hidden-tasks-in-multi","title":"Adversarial Attacks on Hidden Tasks in Multi-Task Learning","date":"2024-05-24","arxiv_id":"2405.15244","repositories_listed":0,"syntology":null},{"url":null,"slug":"trustworthy-actionable-perturbations","title":"Trustworthy Actionable Perturbations","date":"2024-05-18","arxiv_id":"2405.11195","repositories_listed":0,"syntology":null},{"url":null,"slug":"safeguarding-vision-language-models-against","title":"Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors","date":"2024-05-17","arxiv_id":"2405.10529","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-evaluating-the-robustness-of","title":"Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer","date":"2024-05-15","arxiv_id":"2405.09470","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-transferable-targeted-adversarial","title":"Improving Transferable Targeted Adversarial Attack via Normalized Logit Calibration and Truncated Feature Mixing","date":"2024-05-10","arxiv_id":"2405.06340","repositories_listed":0,"syntology":null},{"url":null,"slug":"bb-patch-blackbox-adversarial-patch-attack","title":"BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimization","date":"2024-05-09","arxiv_id":"2405.06049","repositories_listed":0,"syntology":null},{"url":null,"slug":"untargeted-adversarial-attack-on-knowledge","title":"Untargeted Adversarial Attack on Knowledge Graph Embeddings","date":"2024-05-08","arxiv_id":"2405.10970","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-each-textual-sequence-its-own-improving","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","date":"2024-05-06","arxiv_id":"2405.03097","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-general-black-box-adversarial-attack-on","title":"A General Black-box Adversarial Attack on Graph-based Fake News Detectors","date":"2024-04-24","arxiv_id":"2404.15744","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-privacy-guard-robust-traceable","title":"DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark","date":"2024-04-23","arxiv_id":"2404.14693","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-score-changes-adversarial-attack-on-no","title":"Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives","date":"2024-04-20","arxiv_id":"2404.13277","repositories_listed":0,"syntology":null},{"url":null,"slug":"aed-pada-improving-generalizability-of","title":"AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation","date":"2024-04-19","arxiv_id":"2404.12635","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-identity-injection-for-semantic","title":"Adversarial Identity Injection for Semantic Face Image Synthesis","date":"2024-04-16","arxiv_id":"2404.10408","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-novel-perspective-on-adversarial","title":"Towards a Novel Perspective on Adversarial Examples Driven by Frequency","date":"2024-04-16","arxiv_id":"2404.10202","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-a-robust-toxicity-predictor","title":"Towards Building a Robust Toxicity Predictor","date":"2024-04-09","arxiv_id":"2404.08690","repositories_listed":0,"syntology":null},{"url":null,"slug":"brusleattack-a-query-efficient-score-based","title":"BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack","date":"2024-04-08","arxiv_id":"2404.05311","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-attacks-and-dimensionality-in","title":"Adversarial Attacks and Dimensionality in Text Classifiers","date":"2024-04-03","arxiv_id":"2404.02660","repositories_listed":0,"syntology":null},{"url":null,"slug":"advrepair-provable-repair-of-adversarial","title":"Patch Synthesis for Property Repair of Deep Neural Networks","date":"2024-04-02","arxiv_id":"2404.01642","repositories_listed":0,"syntology":null},{"url":null,"slug":"jailbreaking-prompt-attack-a-controllable","title":"Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models","date":"2024-04-02","arxiv_id":"2404.02928","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-granular-adversarial-attacks-against","title":"Multi-granular Adversarial Attacks against Black-box Neural Ranking Models","date":"2024-04-02","arxiv_id":"2404.01574","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-double-edged-sword-of-input-perturbations","title":"The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness","date":"2024-04-01","arxiv_id":"2404.01356","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosalpure-learning-concept-from-group-images","title":"CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection","date":"2024-03-27","arxiv_id":"2403.18554","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-for-robust-and-explainable","title":"Deep Learning for Robust and Explainable Models in Computer Vision","date":"2024-03-27","arxiv_id":"2403.18674","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-sar-atr-defending-against","title":"Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks","date":"2024-03-27","arxiv_id":"2403.18318","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-attack-leveraging-stable-diffusion","title":"Diffusion Attack: Leveraging Stable Diffusion for Naturalistic Image Attacking","date":"2024-03-21","arxiv_id":"2403.14778","repositories_listed":0,"syntology":null},{"url":null,"slug":"capsule-neural-networks-as-noise-stabilizer","title":"Capsule Neural Networks as Noise Stabilizer for Time Series Data","date":"2024-03-20","arxiv_id":"2403.13867","repositories_listed":0,"syntology":null},{"url":null,"slug":"fmm-attack-a-flow-based-multi-modal","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","date":"2024-03-20","arxiv_id":"2403.13507","repositories_listed":0,"syntology":null},{"url":null,"slug":"as-firm-as-their-foundations-can-open-sourced","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","date":"2024-03-19","arxiv_id":"2403.12693","repositories_listed":0,"syntology":null},{"url":null,"slug":"localstylefool-regional-video-style-transfer","title":"LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model","date":"2024-03-18","arxiv_id":"2403.11656","repositories_listed":0,"syntology":null},{"url":null,"slug":"sscae-semantic-syntactic-and-context-aware","title":"SSCAE -- Semantic, Syntactic, and Context-aware natural language Adversarial Examples generator","date":"2024-03-18","arxiv_id":"2403.11833","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-modified-word-saliency-based-adversarial","title":"A Modified Word Saliency-Based Adversarial Attack on Text Classification Models","date":"2024-03-17","arxiv_id":"2403.11297","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-adversarial-robustness-of-image","title":"Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks","date":"2024-03-15","arxiv_id":"2403.10076","repositories_listed":0,"syntology":null},{"url":null,"slug":"attack-deterministic-conditional-image","title":"Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation","date":"2024-03-13","arxiv_id":"2403.08294","repositories_listed":0,"syntology":null},{"url":null,"slug":"prepared-for-the-worst-a-learning-based","title":"Prepared for the Worst: A Learning-Based Adversarial Attack for Resilience Analysis of the ICP Algorithm","date":"2024-03-08","arxiv_id":"2403.05666","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-infrared-geometry-using-geometry","title":"Adversarial Infrared Geometry: Using Geometry to Perform Adversarial Attack against Infrared Pedestrian Detectors","date":"2024-03-06","arxiv_id":"2403.03674","repositories_listed":0,"syntology":null},{"url":null,"slug":"sar-ae-sfp-sar-imagery-adversarial-example-in","title":"SAR-AE-SFP: SAR Imagery Adversarial Example in Real Physics domain with Target Scattering Feature Parameters","date":"2024-03-02","arxiv_id":"2403.01210","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-deep-reinforcement-learning-through-3","title":"Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey","date":"2024-03-01","arxiv_id":"2403.00420","repositories_listed":0,"syntology":null},{"url":null,"slug":"unraveling-adversarial-examples-against","title":"Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification","date":"2024-02-29","arxiv_id":"2402.19355","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-tracking-robustness-with-auxiliary","title":"Enhancing Tracking Robustness with Auxiliary Adversarial Defense Networks","date":"2024-02-28","arxiv_id":"2402.17976","repositories_listed":0,"syntology":null},{"url":null,"slug":"conformal-shield-a-novel-adversarial-attack","title":"Conformal Shield: A Novel Adversarial Attack Detection Framework for Automatic Modulation Classification","date":"2024-02-27","arxiv_id":"2402.17450","repositories_listed":0,"syntology":null},{"url":null,"slug":"extreme-miscalibration-and-the-illusion-of","title":"Extreme Miscalibration and the Illusion of Adversarial Robustness","date":"2024-02-27","arxiv_id":"2402.17509","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-the-jpeg-resistance-of-adversarial","title":"Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing","date":"2024-02-26","arxiv_id":"2402.16586","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-can-defend-themselves-against","title":"LLMs Can Defend Themselves Against Jailbreaking in a Practical Manner: A Vision Paper","date":"2024-02-24","arxiv_id":"2402.15727","repositories_listed":0,"syntology":null}],"record_sha256":"92cb162b04a8155aaf82d8a943db6bc9a4cc2c23a2bfaba3ca5fa5a903e8fad2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}