ML Security Papers

ML07

Transfer Learning Attack

Exploiting fine-tuning and transfer learning vulnerabilities

86 papers Browse all papers

Monthly publications

Paper types

defense 43

attack 31

benchmark 11

tool 1

Domains

nlp 74

vision 15

multimodal 8

generative 7

federated-learning 3

reinforcement-learning 2

graph 2

audio 1

Co-occurring categories

Other OWASP categories that appear on the same papers

LLM01 Prompt Injection

ML10 Model Poisoning

ML02 Data Poisoning Attack

LLM03 Training Data Poisoning

ML05 Model Theft

ML09 Output Integrity Attack

ML04 Membership Inference Attack

LLM06 Sensitive Information Disclosure

LLM08 Excessive Agency

Top cited papers

SaLoRA: Safety-Alignment Preserved Low-Rank Adaptation

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

Attack via Overfitting: 10-shot Benign Fine-tuning to Jailbreak LLMs

Eliciting Harmful Capabilities by Fine-Tuning On Safeguarded Outputs

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs

Open-weight genome language model safeguards: Assessing robustness via adversarial fine-tuning

Patronus: Identifying and Mitigating Transferable Backdoors in Pre-trained Language Models

Detecting Adversarial Fine-tuning with Auditing Agents

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion

Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment

Browse all 86 papers