conftrace_

fine-tuning attack

13 papers

Explore in graph

Co-occurring keywords

safety alignment (178) large language model (13587) harmful fine-tuning (5) adversarial defense (325) model safety (101) model security (118) model defense (23) harmful content (66) model robustness (480) representation noising (1)

Papers

OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy ACL 2026
CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning ACL 2026
A Robust Unlearning Method with Adaptive Knowledge Guidance and Memory Preservation AAAI 2026
SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025
NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks NAACL 2025
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025
Immunization against harmful fine-tuning attacks EMNLP 2024
On the Vulnerability of Safety Alignment in Open-Access LLMs ACL 2024
Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack NIPS 2024
BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment NIPS 2024
Representation Noising: A Defence Mechanism Against Harmful Finetuning NIPS 2024
Grey-box Extraction of Natural Language Models ICML 2021