REVIEW 7 cited by
Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Conversational large language models are trained to refuse to answer harmful questions. However, emergent jailbreaking techniques can still elicit unsafe outputs, presenting an ongoing challenge for model alignment. To better understand how different jailbreak types circumvent safeguards, this paper analyses model activations on different jailbreak inputs. We find that it is possible to extract a jailbreak vector from a single class of jailbreaks that works to mitigate jailbreak effectiveness from other semantically-dissimilar classes. This may indicate that different kinds of effective jailbreaks operate via a similar internal mechanism. We investigate a potential common mechanism of harmfulness feature suppression, and find evidence that effective jailbreaks noticeably reduce a model's perception of prompt harmfulness. These findings offer actionable insights for developing more robust jailbreak countermeasures and lay the groundwork for a deeper, mechanistic understanding of jailbreak dynamics in language models.
Forward citations
Cited by 7 Pith papers
-
LLMs Encode Harmfulness and Refusal Separately
LLMs encode a separate internal harmfulness direction, distinct from the refusal direction, which is more robust to jailbreaks and adversarial finetuning.
-
LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems
A systematic review that categorizes LLM threats, severity scores, and mitigations across development and operation life cycles and multiple deployment scenarios.
-
Fine-Grained Interpretation of Political Opinions in Large Language Models
Four-dimensional political concept vectors learned from LLM internals can detect and partially steer political leanings better than a single left-right axis.
-
The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
Safety refusal in Llama 3.1 8B is governed by a dominant activation direction plus smaller interpretable directions, and removing prompt tokens that activate these secondary directions can bypass fine-tuned safety.
-
NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Models
A visualization system traces jailbreak attacks through LLM layers and neurons, then fine-tunes the vulnerable neurons to reduce attack success while preserving general ability.
-
SATORI: Static Test Oracle Generation for REST APIs
SATORI statically infers REST API test oracles from OpenAPI specs via LLMs, reporting F1 74.3%, above AGORA+'s 69.3%, with 18 confirmed bugs; the supplied full text, however, is a different paper.
-
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety
A new survey organizes LLM interpretation methods by workflow stage and connects them to safety enhancement strategies and tools, covering around 70 works.
Discussion (0). Continue with ORCID to comment.