backdoor defense

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.

Most implemented papers archive 2025-07-28

30 shown of 59 papers with code (131 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Backdoor Defense via Decoupling the Training Process
  5 Feb 2022 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 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.
• FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
  2 Dec 2021 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e.
• REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
  22 Feb 2025 2 repositories listed Syntology ran 5 of 10 samples · 5 unverified · 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.
• Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
  13 Oct 2024 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 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.
• Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
  25 May 2024 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  Specifically, PDB leverages the home-field advantage of defenders by proactively injecting a defensive backdoor into the model during training.
• Beating Backdoor Attack at Its Own Game
  28 Jul 2023 2 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 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.
• Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
  20 Jul 2023 2 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 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…
• LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
  1 Jan 2021 2 repositories listed
  Under 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…
• ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
  20 Nov 2020 2 repositories listed Syntology ran 3 of 4 samples · 1 unverified
  Nevertheless, there are few studies on defending against textual backdoor attacks.
• CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
  7 Jul 2025 1 repository listed
  CGD utilizes a publicly accessible CLIP model to identify inputs that are likely to be clean or poisoned.
• FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
  17 May 2025 1 repository listed
  In particular, we divide the local model into a feature extractor and a classifier.
• Cert-SSB: Toward Certified Sample-Specific Backdoor Defense
  30 Apr 2025 1 repository listed
  To conquer this challenge, we introduce a storage-update-based certification method, which dynamically adjusts each sample's certification region to improve certification performance.
• TrojanDam: Detection-Free Backdoor Defense in Federated Learning through Proactive Model Robustification utilizing OOD Data
  22 Apr 2025 1 repository listed
  We 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,…
• Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
  28 Feb 2025 1 repository listed
  Existing 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.
• Towards Backdoor Stealthiness in Model Parameter Space
  10 Jan 2025 1 repository listed
  To answer this question, we examine 12 common backdoor attacks that focus on input-space or feature-space stealthiness and 17 diverse representative defenses.
• Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
  5 Jan 2025 1 repository listed
  The BTU defense leverages these properties to identify aberrant embedding parameters and subsequently removes backdoor behaviors using a fine-grained unlearning technique.
• Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining
  3 Dec 2024 1 repository listed
  Backdoor attacks remain significant security threats to generative large language models (LLMs).
• CROW: Eliminating Backdoors from Large Language Models via Internal Consistency Regularization
  18 Nov 2024 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Recent studies reveal that Large Language Models (LLMs) are susceptible to backdoor attacks, where adversaries embed hidden triggers that manipulate model responses.
• BackdoorMBTI: A Backdoor Learning Multimodal Benchmark Tool Kit for Backdoor Defense Evaluation
  17 Nov 2024 1 repository listed
  In 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…
• Expose Before You Defend: Unifying and Enhancing Backdoor Defenses via Exposed Models
  25 Oct 2024 1 repository listed
  Specifically, 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…
• "No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
  2 Oct 2024 1 repository listed
  To achieve this objective, we ask: How to recover universal and hard backdoor triggers in GNNs?
• TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
  9 Sep 2024 1 repository listed
  Additionally, 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…
• Fisher Information guided Purification against Backdoor Attacks
  1 Sep 2024 1 repository listed
  Intuitively, the backdoor can be purified by re-optimizing the model to smoother minima.
• VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification
  28 Aug 2024 1 repository listed
  Subsequently, VFLIP conducts purification which removes the embeddings identified as malicious and reconstructs all the embeddings based on the remaining embeddings.
• Diff-Cleanse: Identifying and Mitigating Backdoor Attacks in Diffusion Models
  31 Jul 2024 1 repository listed
  We evaluate our framework on hundreds of DMs that are attacked by three existing backdoor attack methods with a wide range of hyperparameter settings.
• Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
  28 May 2024 1 repository listed
  Specifically, our PUD has a progressive model purification scheme to jointly erase backdoors and enhance the model's adversarial robustness.
• BadActs: A Universal Backdoor Defense in the Activation Space
  18 May 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage.
• Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
  15 Mar 2024 1 repository listed Syntology ran 4 of 5 samples · 1 unverified · 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.
• Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
  17 Feb 2024 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 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.
• Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
  4 Jan 2024 1 repository listed Syntology ran 5 of 9 samples · 4 unverified · 9 pointer-only (licence)
  Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data.

Syntology lines on 13 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. Read from the graph 2026-09-24.