ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack

Reported by arXiv cs.CR (Yuanwei Wu, Lingdong Huang, Yunlong Mao, Kanye Ye Wang, Jingyu Hua, Sheng Zhong)

Summary by Cyber Security News19 Oct 2026, 06:00 CET

About this summary. This is a short excerpt from the description that arXiv cs.CR published with its article. Cyber Security News did not report or verify the underlying story. Read the original: https://arxiv.org/abs/2610.23030

arXiv:2610.23030v1 Announce Type: new Abstract: Despite extensive safety alignment, large language models remain vulnerable to jailbreak attacks. Existing optimization-based attacks share a single objective: maximize a token-level proxy of victim compliance---such as the likelihood of an affirmative prefix---computed on the prompt rather than the decoded reply.

Read the full article at arXiv cs.CR →

Source attribution: headline and facts are from arXiv cs.CR (arxiv.org). Summary method: excerpt of the source description. See our source attribution policy.

Related coverage

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

Log-To-Leak: Prompt Injection Attacks on Tool-Using LLM Agents via the Model Context Protocol

SpecGuard: Detecting Multi-Turn LLM Jailbreaks via Specification-Based Runtime Monitoring

PrivacyEvalClaw: A Tool-Augmented Deliberative Agent for Auditing Privacy Leakage in LLM Jailbreak Responses

Game Boy Color on My Conference Badge

Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability