ML Security Papers

LLM03

Training Data Poisoning

LLM-specific data poisoning

43 papers Browse all papers

Monthly publications

Paper types

attack 24

defense 13

survey 3

benchmark 2

tool 1

Domains

nlp 43

vision 4

reinforcement-learning 4

federated-learning 4

multimodal 1

graph 1

generative 1

Co-occurring categories

Other OWASP categories that appear on the same papers

ML02 Data Poisoning Attack

ML10 Model Poisoning

LLM01 Prompt Injection

LLM06 Sensitive Information Disclosure

ML07 Transfer Learning Attack

ML06 AI Supply Chain Attacks

ML08 Model Skewing

Top cited papers

Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data

Subliminal Corruption: Mechanisms, Thresholds, and Interpretability

AutoBackdoor: Automating Backdoor Attacks via LLM Agents

Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis

Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment

Incentive-Aware AI Safety via Strategic Resource Allocation: A Stackelberg Security Games Perspective

Understanding and Mitigating Dataset Corruption in LLM Steering

Browse all 43 papers