Skip to main content
LLM Security Database
Skip to research details
Back to research findings
LMVD-ID: 997e3c57
Paper published October 1, 2024
Entry analyzed December 28, 2024
Paper-reported evidence
Confidence: Source-linked

The LMVD-ID is an internal research identifier, not an official CVE identifier.

Multi-Round LLM Jailbreak

A multi-round attack against Large Language Models (LLMs) allows bypassing safety mechanisms by iteratively refining prompts to elicit undesired behavior. The attack leverages the LLM's tendency to adjust its response…

BibTeX citation

Paper-evaluated models

No paper-evaluated models are recorded for this entry.

Description

A multi-round attack against Large Language Models (LLMs) allows bypassing safety mechanisms by iteratively refining prompts to elicit undesired behavior. The attack leverages the LLM's tendency to adjust its response based on preceding interactions, circumventing single-round prompt filtering defenses.

Examples

Unavailable due to paper withdrawal.

Impact

LLMs can be manipulated to generate harmful content, such as hate speech, misinformation, or instructions for illegal activities, despite safety protocols. This undermines trust and safety features implemented in LLM applications.

Affected Systems

All LLMs that employ iterative prompt-response mechanisms and rely solely on single-round prompt filtering for safety.

Paper note: the original mitigation discussion is unavailable because the paper was withdrawn.

Mitigation Steps

  • Reassess the full input and conversation intent before responding or invoking tools, combine model-level alignment with independent input and output policy checks, and avoid relying on a single signature or refusal heuristic.
  • Add a targeted regression using inert data and actions, measure both safety and utility regressions, and monitor production for repeated or adaptive attempts.

Research context and confidence

Evidence and verification
Paper-reported; independent reproduction is not documented.
Primary research source linked.
Severity
Not rated by this catalog.
Source and publication type
arXiv · Research preprint.
Peer-review status is not provided by this source.
Author and publication status
Author metadata is not stored; see the primary paper.
Threat model and attacker access
Black-box model, service, or application access.
Related deployment categories
No related deployment category is classified.
Taxonomy labels only; paper-specific deployment prerequisites are not inferred.
Affected systems
All LLMs that employ iterative prompt-response mechanisms and rely solely on single-round prompt filtering for safety. Paper note: the original mitigation discussion is unavailable because the paper was withdrawn.

Research Paper

Multi-round jailbreak attack on large language models

Primary source: arXiv. Findings are reported by the cited research and have not been independently verified.

View Paper

Evidence

This entry is based on a primary research source. Its findings are paper-reported; independent reproduction and verification are not claimed.

https://arxiv.org/abs/2410.11533