REVIEW 7 cited by
Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
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
read the original abstract
The rapid evolution of multimodal foundation models has led to significant advancements in cross-modal understanding and generation across diverse modalities, including text, images, audio, and video. However, these models remain susceptible to jailbreak attacks, which can bypass built-in safety mechanisms and induce the production of potentially harmful content. Consequently, understanding the methods of jailbreak attacks and existing defense mechanisms is essential to ensure the safe deployment of multimodal generative models in real-world scenarios, particularly in security-sensitive applications. To provide comprehensive insight into this topic, this survey reviews jailbreak and defense in multimodal generative models. First, given the generalized lifecycle of multimodal jailbreak, we systematically explore attacks and corresponding defense strategies across four levels: input, encoder, generator, and output. Based on this analysis, we present a detailed taxonomy of attack methods, defense mechanisms, and evaluation frameworks specific to multimodal generative models. Additionally, we cover a wide range of input-output configurations, including modalities such as Any-to-Text, Any-to-Vision, and Any-to-Any within generative systems. Finally, we highlight current research challenges and propose potential directions for future research. The open-source repository corresponding to this work can be found at https://github.com/liuxuannan/Awesome-Multimodal-Jailbreak.
Forward citations
Cited by 7 Pith papers
-
Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks
Even the best recover-and-decode plus reguard pipeline leaves 63–65% of behaviors broken under best-of-suite attacks, and the reguard fix drives benign over-refusal to 81–92%.
-
V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure
Video LLMs understand harmful content but activate weaker refusal signals when the query is benign; prompt realignment reduces attack success from ~48% to ~1%.
-
Implicit Jailbreak Attacks via Cross-Modal Information Concealment on Vision-Language Models
IJA hides a malicious instruction in image steganography and uses a benign extraction prompt plus iterative template refinement to make multimodal LLMs execute it.
-
Invisible Injections: Exploiting Vision-Language Models Through Steganographic Prompt Embedding
Steganographic prompt injection is reported to covertly manipulate vision-language models with up to 31.8% success, but the evidence is not reproducible.
-
GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention
GIFT immunizes diffusion models against malicious fine-tuning by combining loss maximization and representation noising, preserving safe concept generation.
-
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.
-
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
A survey of LVLM safety that adds a lifecycle taxonomy and new benchmark results showing Janus-Pro-7B has weaker safety than several open-source LVLMs.
Discussion (0). Sign in to comment.