Backdoor Attack

Description from the archive 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

No dataset record in the archive lists this task.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 217 papers with code (523 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.

• BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
  1 Aug 2021 7 repositories listed Syntology ran 4 of 8 samples · 4 unverified · 2 pointer-only (licence)
  In particular, our BadEncoder injects backdoors into a pre-trained image encoder such that the downstream classifiers built based on the backdoored image encoder for different downstream tasks simultaneously inherit the…
• An Embarrassingly Simple Backdoor Attack on Self-supervised Learning
  13 Oct 2022 4 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  As a new paradigm in machine learning, self-supervised learning (SSL) is capable of learning high-quality representations of complex data without relying on labels.
• Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information
  11 Apr 2022 3 repositories listed Syntology ran 2 of 3 samples · 1 unverified
  With poisoning equal to or less than 0.
• 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.
• Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
  5 Jul 2020 3 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  A backdoor attack installs a backdoor into the victim model by injecting a backdoor pattern into a small proportion of the training data.
• Hidden Trigger Backdoor Attacks
  30 Sep 2019 3 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  Backdoor attacks are a form of adversarial attacks on deep networks where the attacker provides poisoned data to the victim to train the model with, and then activates the attack by showing a specific small trigger…
• To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models
  16 Feb 2025 2 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  On the malicious side, we introduce Breaking of Thought (BoT), a novel attack that enables adversaries to bypass the thinking process of LRMs, thereby compromising their reliability and availability.
• Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
  15 Jul 2024 2 repositories listed Syntology ran 2 of 4 samples · 2 unverified · 4 pointer-only (licence)
  We demonstrate that an attacker can embed a backdoor in LLMs, which, when activated by a specific trigger in the input, manipulates the model's uncertainty without affecting the final output.
• Invisible Backdoor Attacks on Diffusion Models
  2 Jun 2024 2 repositories listed Syntology ran 9 of 35 samples · 26 unverified · 19 pointer-only (licence)
  In recent years, diffusion models have achieved remarkable success in the realm of high-quality image generation, garnering increased attention.
• 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.
• Towards Imperceptible Backdoor Attack in Self-supervised Learning
  23 May 2024 2 repositories listed
  In this paper, we propose an imperceptible and effective backdoor attack against self-supervised models.
• Universal Jailbreak Backdoors from Poisoned Human Feedback
  24 Nov 2023 2 repositories listed Syntology ran 1 of 4 samples · 3 unverified
  Reinforcement Learning from Human Feedback (RLHF) is used to align large language models to produce helpful and harmless responses.
• 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.
• Adversarial Feature Map Pruning for Backdoor
  21 Jul 2023 2 repositories listed Syntology ran 6 of 7 samples · 1 unverified · 7 pointer-only (licence)
  Unlike existing defense strategies, which focus on reproducing backdoor triggers, FMP attempts to prune backdoor feature maps, which are trained to extract backdoor information from inputs.
• Backdoor Attacks Against Dataset Distillation
  3 Jan 2023 2 repositories listed Syntology ran 6 of 15 samples · 9 unverified
  A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset.
• CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
  15 Nov 2022 2 repositories listed
  In this work, we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL.
• Neurotoxin: Durable Backdoors in Federated Learning
  12 Jun 2022 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In this type of attack, the goal of the attacker is to use poisoned updates to implant so-called backdoors into the learned model such that, at test time, the model's outputs can be fixed to a given target for certain…
• Triggerless Backdoor Attack for NLP Tasks with Clean Labels
  15 Nov 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  To deal with this issue, in this paper, we propose a new strategy to perform textual backdoor attacks which do not require an external trigger, and the poisoned samples are correctly labeled.
• Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger
  26 May 2021 2 repositories listed Syntology ran 1 of 2 samples · 1 unverified
  As far as we know, almost all existing textual backdoor attack methods insert additional contents into normal samples as triggers, which causes the trigger-embedded samples to be detected and the backdoor attacks to be…
• Backdoor Attacks on Self-Supervised Learning
  21 May 2021 2 repositories listed Syntology ran 8 of 13 samples · 5 unverified · 2 pointer-only (licence)
  We show that such methods are vulnerable to backdoor attacks - where an attacker poisons a small part of the unlabeled data by adding a trigger (image patch chosen by the attacker) to the images.
• Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
  21 Feb 2021 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating…
• 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…
• Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
  21 Dec 2020 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data.
• 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.
• Backdoor Attack against Speaker Verification
  22 Oct 2020 2 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.
• Embedding and Extraction of Knowledge in Tree Ensemble Classifiers
  16 Oct 2020 2 repositories listed
  Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence,…
• Graph Backdoor
  21 Jun 2020 2 repositories listed
  One intriguing property of deep neural networks (DNNs) is their inherent vulnerability to backdoor attacks -- a trojan model responds to trigger-embedded inputs in a highly predictable manner while functioning normally…
• Backdoor Attacks to Graph Neural Networks
  19 Jun 2020 2 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Specifically, we propose a \emph{subgraph based backdoor attack} to GNN for graph classification.
• DBA: Distributed Backdoor Attacks against Federated Learning
  1 May 2020 2 repositories listed
  Compared to standard centralized backdoors, we show that DBA is substantially more persistent and stealthy against FL on diverse datasets such as finance and image data.
• Invisible Backdoor Triggers in Image Editing Model via Deep Watermarking
  5 Jun 2025 1 repository listed
  Diffusion models have achieved remarkable progress in both image generation and editing.

Syntology lines on 23 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.