Backdoor Attack

Backdoor attacks inject maliciously constructed data into a training set so that, at test time, the trained model misclassifies inputs patched with a backdoor trigger as an adversarially-desired target class.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 1–25 of 523 papers

Title	Date	Tasks	Status	Hype	Score
AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases	Jul 17, 2024	Autonomous DrivingBackdoor Attack	CodeCode Available	3	5
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents	Oct 3, 2024	Autonomous DrivingBackdoor Attack	CodeCode Available	3	5
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents	Feb 17, 2024	Backdoor Attackbackdoor defense	CodeCode Available	2	5
Backdoor Learning: A Survey	Jul 17, 2020	Adversarial AttackBackdoor Attack	CodeCode Available	2	5
Test-Time Backdoor Attacks on Multimodal Large Language Models	Feb 13, 2024	Backdoor Attack	CodeCode Available	2	5
BAPLe: Backdoor Attacks on Medical Foundational Models using Prompt Learning	Aug 14, 2024	Backdoor AttackPrompt Learning	CodeCode Available	2	5
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models	Jan 20, 2024	Backdoor Attack	CodeCode Available	2	5
An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection	Jun 10, 2024	Backdoor AttackCode Completion	CodeCode Available	2	5
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label	Jul 1, 2022	Adversarial AttackBackdoor Attack	CodeCode Available	1	5
BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning	Nov 20, 2023	Backdoor AttackContrastive Learning	CodeCode Available	1	5
BadEdit: Backdooring large language models by model editing	Mar 20, 2024	Backdoor Attackknowledge editing	CodeCode Available	1	5
BadCM: Invisible Backdoor Attack Against Cross-Modal Learning	Oct 3, 2024	Backdoor AttackCross-Modal Retrieval	CodeCode Available	1	5
Backdoor Attacks Against Dataset Distillation	Jan 3, 2023	Backdoor AttackDataset Distillation	CodeCode Available	1	5
BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning	Aug 1, 2021	Backdoor AttackSelf-Supervised Learning	CodeCode Available	1	5
BadMerging: Backdoor Attacks Against Model Merging	Aug 14, 2024	Backdoor Attackmodel	CodeCode Available	1	5
Backdoor Defense via Deconfounded Representation Learning	Mar 13, 2023	Backdoor Attackbackdoor defense	CodeCode Available	1	5
Anti-Backdoor Learning: Training Clean Models on Poisoned Data	Oct 22, 2021	Backdoor Attack	CodeCode Available	1	5
Backdoor Attack with Sparse and Invisible Trigger	May 11, 2023	Backdoor Attack	CodeCode Available	1	5
Backdoor Attacks on Federated Learning with Lottery Ticket Hypothesis	Sep 22, 2021	Backdoor AttackFederated Learning	CodeCode Available	1	5
Anti-Distillation Backdoor Attacks: Backdoors Can Really Survive in Knowledge Distillation	Oct 24, 2021	Backdoor AttackKnowledge Distillation	CodeCode Available	1	5
Backdoor Attacks on Self-Supervised Learning	May 21, 2021	Backdoor AttackInductive Bias	CodeCode Available	1	5
Backdoor Attacks for Remote Sensing Data with Wavelet Transform	Nov 15, 2022	Backdoor Attackbackdoor defense	CodeCode Available	1	5
Backdoor Attack against Speaker Verification	Oct 22, 2020	Backdoor AttackClustering	CodeCode Available	1	5
Can We Mitigate Backdoor Attack Using Adversarial Detection Methods?	Jun 26, 2020	Adversarial DefenseBackdoor Attack	CodeCode Available	1	5
A new Backdoor Attack in CNNs by training set corruption without label poisoning	Feb 12, 2019	Backdoor AttackGeneral Classification	CodeCode Available	1	5

Show:10 25 50

← PrevPage 1 of 21Next →

No leaderboard results yet.