all InfoSec news
Jailbreaking is Best Solved by Definition
March 25, 2024, 4:11 a.m. | Taeyoun Kim, Suhas Kotha, Aditi Raghunathan
cs.CR updates on arXiv.org arxiv.org
Abstract: The rise of "jailbreak" attacks on language models has led to a flurry of defenses aimed at preventing the output of undesirable responses. In this work, we critically examine the two stages of the defense pipeline: (i) the definition of what constitutes unsafe outputs, and (ii) the enforcement of the definition via methods such as input processing or fine-tuning. We cast severe doubt on the efficacy of existing enforcement mechanisms by showing that they fail …
arxiv attacks cs.cl cs.cr cs.lg defense defenses definition enforcement jailbreak jailbreaking language language models led pipeline work
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Information Security Engineers
@ D. E. Shaw Research | New York City
Technology Security Analyst
@ Halton Region | Oakville, Ontario, Canada
Senior Cyber Security Analyst
@ Valley Water | San Jose, CA
Sr. Staff Firmware Engineer – Networking & Firewall
@ Axiado | Bengaluru, India
Compliance Architect / Product Security Sr. Engineer/Expert (f/m/d)
@ SAP | Walldorf, DE, 69190
SAP Security Administrator
@ FARO Technologies | EMEA-Portugal