Browse State-of-the-Art › backdoor defense
backdoor defense
59 papers with code · 0 benchmarks · 2 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
2 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 131 · with a code link: 59 · where Syntology ran a sample: 26 (20 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (26 of 131 tagged: 20 with a run with no instrument failure, 6 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 131, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
5 Feb 2022 3 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 1 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; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples.
-
2 Dec 2021 3 repositories listed Syntology community repositories only · 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 (of 2 harvested samples)However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e. g., X-Ray, CT, and MRI) and analysis tasks (e. g., classification…
-
22 Feb 2025 2 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified (of 10 harvested samples) · 10 pointer-only (licence)Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase.
-
13 Oct 2024 2 repositories listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample) · 1 pointer-only (licence)We find that current safety purification methods are vulnerable to the rapid re-learning of backdoor behavior, even when further fine-tuning of purified models is performed using a very small number of poisoned samples.
-
25 May 2024 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Specifically, PDB leverages the home-field advantage of defenders by proactively injecting a defensive backdoor into the model during training.
-
28 Jul 2023 2 repositories listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence)Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added.
-
20 Jul 2023 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk, which mainly captures the risk on the shared adversarial examples (SAEs) between the backdoored…
-
1 Jan 2021 2 repositories listedUnder this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on…
-
20 Nov 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 3 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; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)Nevertheless, there are few studies on defending against textual backdoor attacks.
-
7 Jul 2025 1 repository listedCGD utilizes a publicly accessible CLIP model to identify inputs that are likely to be clean or poisoned.
-
17 May 2025 1 repository listedIn particular, we divide the local model into a feature extractor and a classifier.
-
30 Apr 2025 1 repository listedTo conquer this challenge, we introduce a storage-update-based certification method, which dynamically adjusts each sample's certification region to improve certification performance.
-
22 Apr 2025 1 repository listedWe proceed to prove the feasibility of activating redundant neurons utilizing out-of-distribution (OOD) samples in centralized settings, and migrating to FL settings to propose a novel backdoor defense mechanism…
-
28 Feb 2025 1 repository listedExisting defense strategies are well equipped to thwart such attacks through backdoor detection and trigger inversion because previous attack methods are constrained by limited input spaces and low-dimensional triggers.
-
10 Jan 2025 1 repository listedTo answer this question, we examine 12 common backdoor attacks that focus on input-space or feature-space stealthiness and 17 diverse representative defenses.
-
5 Jan 2025 1 repository listedThe BTU defense leverages these properties to identify aberrant embedding parameters and subsequently removes backdoor behaviors using a fine-grained unlearning technique.
-
3 Dec 2024 1 repository listedBackdoor attacks remain significant security threats to generative large language models (LLMs).
-
18 Nov 2024 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)Recent studies reveal that Large Language Models (LLMs) are susceptible to backdoor attacks, where adversaries embed hidden triggers that manipulate model responses.
-
17 Nov 2024 1 repository listedIn order to facilitate the research in multimodal backdoor, we introduce BackdoorMBTI, the first backdoor learning toolkit and benchmark designed for multimodal evaluation across three representative modalities from…
-
25 Oct 2024 1 repository listedSpecifically, EBYD first exposes the backdoor functionality in the backdoored model through a model preprocessing step called backdoor exposure, and then applies detection and removal methods to the exposed model to…
-
2 Oct 2024 1 repository listedTo achieve this objective, we ask: How to recover universal and hard backdoor triggers in GNNs?
-
9 Sep 2024 1 repository listedAdditionally, with the reversed trigger, we propose backdoor detection from the noise space, introducing the first backdoor input detection approach for diffusion models and a novel model detection algorithm that…
-
1 Sep 2024 1 repository listedIntuitively, the backdoor can be purified by re-optimizing the model to smoother minima.
-
28 Aug 2024 1 repository listedSubsequently, VFLIP conducts purification which removes the embeddings identified as malicious and reconstructs all the embeddings based on the remaining embeddings.
-
31 Jul 2024 1 repository listedWe evaluate our framework on hundreds of DMs that are attacked by three existing backdoor attack methods with a wide range of hyperparameter settings.
-
28 May 2024 1 repository listedSpecifically, our PUD has a progressive model purification scheme to jointly erase backdoors and enhance the model's adversarial robustness.
-
18 May 2024 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage.
-
15 Mar 2024 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 5 pointer-only (licence)Based on this, we pose the backdoor data identification problem as a hierarchical data splitting optimization problem, leveraging a novel SPC-based loss function as the primary optimization objective.
-
17 Feb 2024 1 repository listed Syntology official (archive's flag): 2 ran · 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 (of 2 harvested samples) · 2 pointer-only (licence)In this work, we take the first step to investigate one of the typical safety threats, backdoor attack, to LLM-based agents.
-
4 Jan 2024 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence)Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data.
-
20 Dec 2023 1 repository listed
-
13 Dec 2023 1 repository listed
-
4 Dec 2023 1 repository listed
-
4 Nov 2023 1 repository listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
21 Sep 2023 1 repository listed
-
21 Sep 2023 1 repository listed
-
18 Aug 2023 1 repository listed
-
30 Jun 2023 1 repository listed
-
29 Jun 2023 1 repository listed
-
24 May 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
24 May 2023 1 repository listed
-
7 May 2023 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
27 Mar 2023 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified (of 15 harvested samples) · 3 pointer-only (licence)
-
23 Mar 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
21 Mar 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
13 Mar 2023 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
22 Feb 2023 1 repository listed Syntology official (archive's flag): 3 ran · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 2 pointer-only (licence)
-
15 Nov 2022 1 repository listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 1 pointer-only (licence)
-
10 Nov 2022 1 repository listed
-
2 Nov 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
1 Nov 2022 1 repository listed
-
23 Oct 2022 1 repository listed Syntology official (archive's flag): 1 ran · 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 (of 1 harvested sample) · 1 pointer-only (licence)
-
14 Oct 2022 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)
-
12 Oct 2022 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
13 May 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
9 May 2022 1 repository listed
-
21 Apr 2022 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)
-
9 Mar 2020 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
6 Mar 2020 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)
-
CUBA: Controlled Untargeted Backdoor Attack against Deep Neural Networks20 Jun 2025 0 repositories listed
-
InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning14 Jun 2025 0 repositories listed
-
TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks12 Jun 2025 0 repositories listed
-
SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs5 Jun 2025 0 repositories listed
-
Robust Anti-Backdoor Instruction Tuning in LVLMs4 Jun 2025 0 repositories listed
-
Spectral Insights into Data-Oblivious Critical Layers in Large Language Models31 May 2025 0 repositories listed
-
Heterogeneous Graph Backdoor Attack30 May 2025 0 repositories listed
-
Backdoor Defense in Diffusion Models via Spatial Attention Unlearning21 Apr 2025 0 repositories listed
-
Decoupled Distillation to Erase: A General Unlearning Method for Any Class-centric Tasks31 Mar 2025 0 repositories listed
-
Prototype Guided Backdoor Defense26 Mar 2025 0 repositories listed
-
A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models26 Feb 2025 0 repositories listed
-
Class-Conditional Neural Polarizer: A Lightweight and Effective Backdoor Defense by Purifying Poisoned Features23 Feb 2025 0 repositories listed
-
Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition3 Feb 2025 0 repositories listed
-
PCAP-Backdoor: Backdoor Poisoning Generator for Network Traffic in CPS/IoT Environments26 Jan 2025 0 repositories listed
-
Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning29 Dec 2024 0 repositories listed
-
Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images11 Dec 2024 0 repositories listed
-
CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models2 Dec 2024 0 repositories listed
-
Neutralizing Backdoors through Information Conflicts for Large Language Models27 Nov 2024 0 repositories listed
-
MADE: Graph Backdoor Defense with Masked Unlearning26 Nov 2024 0 repositories listed
-
FedBlock: A Blockchain Approach to Federated Learning against Backdoor Attacks5 Nov 2024 0 repositories listed
-
Embedding Watermarks in Diffusion Process for Model Intellectual Property Protection29 Oct 2024 0 repositories listed
-
BeniFul: Backdoor Defense via Middle Feature Analysis for Deep Neural Networks15 Oct 2024 0 repositories listed
-
Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats29 Sep 2024 0 repositories listed
-
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning26 Sep 2024 0 repositories listed
-
Adversarial Backdoor Defense in CLIP24 Sep 2024 0 repositories listed
-
Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis24 Sep 2024 0 repositories listed
-
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm21 Sep 2024 0 repositories listed
-
Data-centric NLP Backdoor Defense from the Lens of Memorization21 Sep 2024 0 repositories listed
-
PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models20 Sep 2024 0 repositories listed
-
Backdoor defense, learnability and obfuscation4 Sep 2024 0 repositories listed
-
Backdoor Defense through Self-Supervised and Generative Learning2 Sep 2024 0 repositories listed
-
Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks28 Aug 2024 0 repositories listed
-
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation28 Aug 2024 0 repositories listed
-
SAB:A Stealing and Robust Backdoor Attack based on Steganographic Algorithm against Federated Learning25 Aug 2024 0 repositories listed
-
Protecting against simultaneous data poisoning attacks23 Aug 2024 0 repositories listed
-
Eliminating Backdoors in Neural Code Models for Secure Code Understanding8 Aug 2024 0 repositories listed
-
Model-agnostic clean-label backdoor mitigation in cybersecurity environments11 Jul 2024 0 repositories listed
-
Evolutionary Trigger Detection and Lightweight Model Repair Based Backdoor Defense7 Jul 2024 0 repositories listed
-
Defense Against Syntactic Textual Backdoor Attacks with Token Substitution4 Jul 2024 0 repositories listed
-
14 Jun 2024 0 repositories listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness30 May 2024 0 repositories listed
Syntology lines on 31 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections