all InfoSec news
Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refinement
Feb. 26, 2024, 5:11 a.m. | Heegyu Kim, Sehyun Yuk, Hyunsouk Cho
cs.CR updates on arXiv.org arxiv.org
Abstract: Caution: This paper includes offensive words that could potentially cause unpleasantness. Language models (LMs) are vulnerable to exploitation for adversarial misuse. Training LMs for safety alignment is extensive and makes it hard to respond to fast-developing attacks immediately, such as jailbreaks. We propose self-refine with formatting that achieves outstanding safety even in non-safety-aligned LMs and evaluate our method alongside several defense baselines, demonstrating that it is the safest training-free method against jailbreak attacks. Additionally, we …
adversarial alignment arxiv attacks cs.cl cs.cr cs.lg defense exploitation fast hard jailbreak language language models lms offensive refine respond safety training vulnerable
More from arxiv.org / cs.CR updates on arXiv.org
IDEA: Invariant Defense for Graph Adversarial Robustness
2 days, 7 hours ago |
arxiv.org
FairCMS: Cloud Media Sharing with Fair Copyright Protection
2 days, 7 hours ago |
arxiv.org
Efficient unitary designs and pseudorandom unitaries from permutations
2 days, 7 hours ago |
arxiv.org
Jobs in InfoSec / Cybersecurity
SOC 2 Manager, Audit and Certification
@ Deloitte | US and CA Multiple Locations
Security Officer Hospital Laguna Beach
@ Allied Universal | Laguna Beach, CA, United States
Sr. Cloud DevSecOps Engineer
@ Oracle | NOIDA, UTTAR PRADESH, India
Cloud Operations Security Engineer
@ Elekta | Crawley - Cornerstone
Cybersecurity – Senior Information System Security Manager (ISSM)
@ Boeing | USA - Seal Beach, CA
Engineering -- Tech Risk -- Security Architecture -- VP -- Dallas
@ Goldman Sachs | Dallas, Texas, United States