[WIP] Jailbreak Paradox: The Achilles' Heel of LLMs

Abhinav Rao; Monojit Choudhury; Somak Aditya

[WIP] Jailbreak Paradox: The Achilles' Heel of LLMs

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2406.12702 v2 pith:QYNPNYIZ submitted 2024-06-18 cs.CL

Abhinav Rao , Monojit Choudhury , Somak Aditya This is my paper

classification cs.CL

keywords jailbreakmodelparadoxesachillesbroadercannotcaseclassifier

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

We introduce two paradoxes concerning jailbreak of foundation models: First, it is impossible to construct a perfect jailbreak classifier, and second, a weaker model cannot consistently detect whether a stronger (in a pareto-dominant sense) model is jailbroken or not. We provide formal proofs for these paradoxes and a short case study on Llama and GPT4-o to demonstrate this. We discuss broader theoretical and practical repercussions of these results.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection
cs.CR 2025-08 conditional novelty 5.0 of 10

RTST, a two-agent moderator with an explainable Behavior ledger and per-prompt weight updates, reduced attack success rate from 12-63% to 0-17% on three jailbreak benchmarks with Gemini 2.5 Flash.

Pith tools