Pith. sign in

REVIEW 1 cited by

Continuous Embedding Attacks via Clipped Inputs in Jailbreaking 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

arxiv 2407.13796 v1 pith:P7RPD755 submitted 2024-07-16 cs.CR cs.AIcs.CL

classification cs.CRcs.AIcs.CL
keywords continuousinputsattacksclipdiscretejailbreakinglanguagelarge
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Security concerns for large language models (LLMs) have recently escalated, focusing on thwarting jailbreaking attempts in discrete prompts. However, the exploration of jailbreak vulnerabilities arising from continuous embeddings has been limited, as prior approaches primarily involved appending discrete or continuous suffixes to inputs. Our study presents a novel channel for conducting direct attacks on LLM inputs, eliminating the need for suffix addition or specific questions provided that the desired output is predefined. We additionally observe that extensive iterations often lead to overfitting, characterized by repetition in the output. To counteract this, we propose a simple yet effective strategy named CLIP. Our experiments show that for an input length of 40 at iteration 1000, applying CLIP improves the ASR from 62% to 83%

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift

    cs.CR 2025-09 conditional novelty 6.0 of 10

    Small single-dimension perturbations to embeddings of high-risk tokens can flip aligned LLM responses from refusal to harmful output, and a search algorithm (SEP) locates such perturbations across models.

Pith tools