ML Security Papers

LLM03

Training Data Poisoning

LLM-specific data poisoning

51 papers Browse all papers

Monthly publications

Paper types

attack 28

defense 16

survey 3

benchmark 3

tool 1

Domains

nlp 51

reinforcement-learning 4

federated-learning 4

vision 4

generative 2

graph 1

multimodal 1

Co-occurring categories

Other OWASP categories that appear on the same papers

ML02 Data Poisoning Attack

ML10 Model Poisoning

LLM01 Prompt Injection

ML07 Transfer Learning Attack

LLM06 Sensitive Information Disclosure

ML06 AI Supply Chain Attacks

LS06 Red-Team Agents

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

AutoBackdoor: Automating Backdoor Attacks via LLM Agents

Subliminal Corruption: Mechanisms, Thresholds, and Interpretability

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

Cost-Minimized Label-Flipping Poisoning Attack to LLM Alignment

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

RAG-targeted Adversarial Attack on LLM-based Threat Detection and Mitigation Framework

Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models

Browse all 51 papers