data poisoning

128 papers

Explore in graph

Also known as

DPCL

Co-occurring keywords

backdoor attack (377) adversarial attack (1599) adversarial learning (1592) poisoning attack (97) adversarial defense (324) adversarial robustness (1335) adversarial training (1261) model security (118) backdoor defense (54) large language model (12755)

Papers

Safeguarding Fraud Detection from Attacks: A Robust Graph Learning Approach IJCAI 2024

PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics NIPS 2024

BrainWash: A Poisoning Attack to Forget in Continual Learning CVPR 2024

TrojFSP: Trojan Insertion in Few-shot Prompt Tuning NAACL 2024

Adversarial Backdoor Attack by Naturalistic Data Poisoning on Trajectory Prediction in Autonomous Driving CVPR 2024

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor NIPS 2024

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection NAACL 2024

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE NAACL 2024

Backdoor NLP Models via AI-Generated Text COLING 2024

Data Poisoning based Backdoor Attacks to Contrastive Learning CVPR 2024

How Susceptible are Large Language Models to Ideological Manipulation? EMNLP 2024

Backdoor Attacks via Machine Unlearning AAAI 2024

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models NIPS 2024

Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions EMNLP 2024

2D-OOB: Attributing Data Contribution Through Joint Valuation Framework NIPS 2024

Game-Theoretic Unlearnable Example Generator AAAI 2024

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models NAACL 2024

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors NAACL 2024

Optimistic Verifiable Training by Controlling Hardware Nondeterminism NIPS 2024

Progressive Poisoned Data Isolation for Training-Time Backdoor Defense AAAI 2024

Revamping Federated Learning Security from a Defender's Perspective: A Unified Defense with Homomorphic Encrypted Data Space CVPR 2024

Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models NIPS 2024

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise AAAI 2024

Poisoning-Based Backdoor Attacks in Computer Vision AAAI 2023

Black-Box Data Poisoning Attacks on Crowdsourcing IJCAI 2023