FlipAttack: Jailbreak LLMs via Flipping
pith:DX2EIEY3 Add to your LaTeX paper
What is a Pith Number?\usepackage{pith}
\pithnumber{DX2EIEY3}
Prints a linked pith:DX2EIEY3 badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more
read the original abstract
This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we reveal that LLMs tend to understand the text from left to right and find that they struggle to comprehend the text when noise is added to the left side. Motivated by these insights, we propose to disguise the harmful prompt by constructing left-side noise merely based on the prompt itself, then generalize this idea to 4 flipping modes. Second, we verify the strong ability of LLMs to perform the text-flipping task, and then develop 4 variants to guide LLMs to denoise, understand, and execute harmful behaviors accurately. These designs keep FlipAttack universal, stealthy, and simple, allowing it to jailbreak black-box LLMs within only 1 query. Experiments on 8 LLMs demonstrate the superiority of FlipAttack. Remarkably, it achieves $\sim$98\% attack success rate on GPT-4o, and $\sim$98\% bypass rate against 5 guardrail models on average. The codes are available at GitHub\footnote{https://github.com/yueliu1999/FlipAttack}.
This paper has not been read by Pith yet.
Forward citations
Cited by 6 Pith papers
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
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...
-
Jailbreaking Frontier Foundation Models Through Intention Deception
A multi-turn intention-deception jailbreak achieves high success on GPT-5 and Claude models while exposing para-jailbreaking where models leak harmful information without direct refusal.
-
When Efficiency Backfires: Cascading LLMs Trigger Cascade Failure under Adversarial Attack
LLM cascade systems are vulnerable to a new adversarial attack that simultaneously degrades accuracy and destroys the intended cost savings by targeting both the lightweight models and the escalation decision mechanism.
-
Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain
CoRT achieves 95% average attack success rate on nine LLMs by using iterative risk-concealing prompts and a controller that scores concealment levels on a new 522-instruction financial risk benchmark.
-
SoK: Robustness in Large Language Models against Jailbreak Attacks
The paper taxonomizes jailbreak attacks and defenses for LLMs, introduces the Security Cube multi-dimensional evaluation framework, benchmarks 13 attacks and 5 defenses, and identifies open challenges in LLM robustness.
-
SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
SAID is a training-free defense that distills obfuscated prompts into intents, probes them with safety prefixes, and rejects if any intent is unsafe, claiming SOTA jailbreak resistance on open LLMs.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.