REVIEW 12 cited by
Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks
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
Signed reviews
read the original abstract
The recent release of GPT-4o has garnered widespread attention due to its powerful general capabilities. While its impressive performance is widely acknowledged, its safety aspects have not been sufficiently explored. Given the potential societal impact of risky content generated by advanced generative AI such as GPT-4o, it is crucial to rigorously evaluate its safety. In response to this question, this paper for the first time conducts a rigorous evaluation of GPT-4o against jailbreak attacks. Specifically, this paper adopts a series of multi-modal and uni-modal jailbreak attacks on 4 commonly used benchmarks encompassing three modalities (ie, text, speech, and image), which involves the optimization of over 4,000 initial text queries and the analysis and statistical evaluation of nearly 8,000+ response on GPT-4o. Our extensive experiments reveal several novel observations: (1) In contrast to the previous version (such as GPT-4V), GPT-4o has enhanced safety in the context of text modality jailbreak; (2) The newly introduced audio modality opens up new attack vectors for jailbreak attacks on GPT-4o; (3) Existing black-box multimodal jailbreak attack methods are largely ineffective against GPT-4o and GPT-4V. These findings provide critical insights into the safety implications of GPT-4o and underscore the need for robust alignment guardrails in large models. Our code is available at \url{https://github.com/NY1024/Jailbreak_GPT4o}.
Forward citations
Cited by 12 Pith papers
-
Whose Refusal Is It? The Unmeasured Contribution of Black-Box Multimodal Guardrails
The reported benefit of a multimodal guardrail is a sum of guard blocks and the target model's own refusals, and evaluation protocol alone can move the guardrail's measured share from 0% to 99%.
-
Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink
Adversarial images optimized to induce attention sink behavior increase hallucination rates in multiple MLLMs, including commercial APIs, without visibly degrading response quality.
-
Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
Shuffling words and image patches in harmful prompts bypasses safety mechanisms of several commercial and open-source multimodal models, and a black-box search over shuffles raises attack success rates substantially.
-
A Synonymous Variational Perspective on the Rate-Distortion-Perception Tradeoff
Synset-based reconstruction and synonymous variational inference are claimed to derive the distributional divergence in RDP and unify it with classical rate-distortion theory.
-
Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis
An adversarial training framework pairs a sneaky error generator with an error-diagnosing model, improving stealth and diagnosis on math problems.
-
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
AJailBench is an open benchmark showing that large audio-language models can be jailbroken through TTS-converted text attacks and through subtle acoustic perturbations that preserve speech semantics.
-
REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLM
REVEAL, a new automated benchmark, reports that vision-language models show higher conversation-level defect rates in multi-turn image-input conversations than in single-turn ones across sexual harm, violence, and mis...
-
Manipulating Multimodal Agents via Cross-Modal Prompt Injection
A coordinated attack that embeds malicious cues in both visual and textual inputs can hijack black-box multimodal agents, outperforming single-modality prompt injection attacks.
-
POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models
POISONCRAFT injects adversarial documents into a RAG knowledge base that are likely to be retrieved for arbitrary user queries and that steer the language model into recommending a fake URL.
-
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination
A new jailbreak framework, HACA, combines atomic text and image attack strategies selected by a cross-modal planner and generates attacks with LLMs and text-to-image models, reaching 95.48% average attack success acro...
-
Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models
A survey that organizes audio and video AI security research into adversarial, backdoor, and jailbreak attacks, with extra attention to multimodal large language models.
-
PRJ: Perception-Retrieval-Judgement for Generated Images
A new safety checker for AI-generated images, built from a vision-language model, retrieval-augmented knowledge lookup, and an LLM judge, reports higher detection rates and category-level toxicity scores than three ex...
Discussion (0). Continue with ORCID to comment.