Pith. sign in

REVIEW 4 cited by

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking 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 2505.10838 v1 pith:X4NSOE73 submitted 2025-05-16 cs.LG cs.CLcs.CR

Ran Li , Hao Wang , Chengzhi Mao This is my paper
classification cs.LGcs.CLcs.CR
keywords latentlargooptimizationadversarialattackgradientjailbreakinglanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Efficient red-teaming method to uncover vulnerabilities in Large Language Models (LLMs) is crucial. While recent attacks often use LLMs as optimizers, the discrete language space make gradient-based methods struggle. We introduce LARGO (Latent Adversarial Reflection through Gradient Optimization), a novel latent self-reflection attack that reasserts the power of gradient-based optimization for generating fluent jailbreaking prompts. By operating within the LLM's continuous latent space, LARGO first optimizes an adversarial latent vector and then recursively call the same LLM to decode the latent into natural language. This methodology yields a fast, effective, and transferable attack that produces fluent and stealthy prompts. On standard benchmarks like AdvBench and JailbreakBench, LARGO surpasses leading jailbreaking techniques, including AutoDAN, by 44 points in attack success rate. Our findings demonstrate a potent alternative to agentic LLM prompting, highlighting the efficacy of interpreting and attacking LLM internals through gradient optimization.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

    cs.CL 2026-05 unverdicted novelty 8.0 of 10

    REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reason...

  2. LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models

    cs.CL 2026-05 unverdicted novelty 7.0 of 10

    LASH adaptively composes multiple jailbreak seed prompts via genetic search over subsets and mixture weights to reach 84.5% keyword ASR and 74.5% two-stage ASR on JailbreakBench while using only 30 queries per prompt.

  3. REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-sou...

  4. Echoes of Human Malice in Agents: Benchmarking LLMs for Multi-Turn Online Harassment Attacks

    cs.AI 2025-10 conditional novelty 5.0 of 10

    Fine-tuning an LLM on synthetic toxic dialogues makes it harass in 95–97% of multi-turn conversations in Llama and ~99% in Gemini; memory and planning attacks also raise closed-source vulnerability.

Pith tools