pith. sign in

Tree of attacks: Jailbreaking black-box llms automatically

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

baseline 1

citation-polarity summary

fields

cs.CL 1 cs.CR 1

years

2026 2

verdicts

UNVERDICTED 2

roles

baseline 1

polarities

baseline 1

representative citing papers

LLM-Agnostic Semantic Representation Attack

cs.CL · 2026-05-09 · unverdicted · novelty 6.0

SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.

citing papers explorer

Showing 2 of 2 citing papers.

  • LLM-Agnostic Semantic Representation Attack cs.CL · 2026-05-09 · unverdicted · none · ref 53

    SRA achieves 99.71% average attack success across 26 LLMs by optimizing for coherent malicious semantics via the SRHS algorithm, with claimed theoretical guarantees on convergence and transfer.

  • The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems cs.CR · 2026-04-13 · unverdicted · none · ref 20

    Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.