REVIEW 24 cited by
Jailbreaking Attack against Multimodal Large Language Model
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
Jailbreaking Attack against Multimodal Large Language Model
read the original abstract
This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries. A maximum likelihood-based algorithm is proposed to find an \emph{image Jailbreaking Prompt} (imgJP), enabling jailbreaks against MLLMs across multiple unseen prompts and images (i.e., data-universal property). Our approach exhibits strong model-transferability, as the generated imgJP can be transferred to jailbreak various models, including MiniGPT-v2, LLaVA, InstructBLIP, and mPLUG-Owl2, in a black-box manner. Moreover, we reveal a connection between MLLM-jailbreaks and LLM-jailbreaks. As a result, we introduce a construction-based method to harness our approach for LLM-jailbreaks, demonstrating greater efficiency than current state-of-the-art methods. The code is available here. \textbf{Warning: some content generated by language models may be offensive to some readers.}
Forward citations
Cited by 24 Pith papers
-
Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs
Jailbreak vulnerability in MLLMs is language- and modality-dependent, producing rank reversals in model safety between English and Spanish conditions.
-
RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs
RouteHijack is a routing-aware jailbreak that identifies safety-critical experts via activation contrast and optimizes suffixes to suppress them, reaching 69.3% average attack success rate on seven MoE LLMs with stron...
-
MASCing: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
MASCing uses an LSTM surrogate and optimized steering masks to enable flexible, inference-time control over MoE expert routing for safety objectives, improving jailbreak defense and content generation success rates su...
-
DeepBias: Adaptive In-depth Probing of Social Biases in LVLMs
A generation-evolution-probing loop with Proposer and Digger agents produces DeepBiasBench, exposing deeper LVLM social biases than static image-question benchmarks.
-
Visual Token Compression Enhances Robustness of MLLMs
Pruning visual tokens farthest from the text feature space at selected 'robust' layers improves MLLM jailbreak defense (average +13.29% RAR) and slightly reduces hallucination.
-
3D FaceShell: Attribute Transfer in 3D Face Avatars as a VLM Defense Mechanism
An optimized, view-consistent 3D Gaussian shell around a face avatar reliably changes which facial attributes vision-language models report, while preserving identity and appearance.
-
PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
Existing MLLM unlearning methods reduce private-attribute leakage on entangled images but substantially harm co-occurring public figures and landmarks, with private knowledge often re-emerging after public finetuning.
-
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
A lightweight multi-instance contrastive classifier on MLLM hidden states predicts output harmfulness, matching input-side safety while sharply lowering over-refusal.
-
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges
Introduces MM-Privacy dataset and evaluations showing MLLMs leak sensitive data from images in various tasks, highlighting task inconsistency effects.
-
Investigating Adversarial Robustness of Multi-modal Large Language Models
Robust vision encoders from multimodal adversarial pretraining transfer to MLLMs and deliver large gains in adversarial captioning and VQA performance, while test-time stochastic transformations provide an effective b...
-
Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models
Attention Hijacking is a new attack that improves cross-query transferability in VLMs by explicitly steering internal attention to a persistent image-dominant pattern.
-
SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models
SafeSteer improves safety in multimodal large language models by up to 33.4% via a decoding probe and modal alignment vector without any fine-tuning.
-
Securing Multimodal AI through Internal Information Decomposition
A one-class detector using first-token distributional consistency between text-only, vision-only, and joint predictions reduces multimodal jailbreak attack success rates to below 15% with ~2.4% utility loss.
-
Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs
MemJack achieves 71.48% attack success rate on unmodified COCO val2017 images against Qwen3-VL-Plus by coordinating agents to map visual entities to malicious intents, apply multi-angle camouflage, and filter refusals...
-
TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
TEMPLATEFUZZ mutates chat templates with element-level rules and heuristic search to reach 98.2% average jailbreak success rate on twelve open-source LLMs while degrading accuracy by only 1.1%.
-
RedDiffuser: Auditing Multimodal Safety Failures in Vision-Language Models via Reinforced Diffusion
RedDiffuser is a reinforced diffusion framework that generates adversarial visual contexts to audit and expose widespread multimodal safety failures in VLMs, increasing unsafe response rates by up to 10.69% on LLaVA w...
-
PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models
PHANTOM is a consolidated open-source dataset of 47,524 multimodal adversarial samples for VLMs, extending prior benchmarks across 10 high-level categories and 55 subcategories of harmful intents.
-
Auditing Inference-Time Defense Evaluation for Multimodal Large Language Models
Stacking inference-time defenses for multimodal LLMs drives 97–100% over-refusal of benign queries; no single defense dominates and a simple prompt is often preferable.
-
Auditing Inference-Time Defense Evaluation for Multimodal Large Language Models
An audit of a multimodal-LLM defense-evaluation archive finds three benchmark branches fail provenance checks, the surviving keyword-protocol results are not validated harmlessness rates, and the archive does not supp...
-
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.
-
Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language Models
Attention-guided stage-wise cropping attacks beat random-crop baselines on targeted adversarial attacks for LVLMs, with less visible perturbation.
-
Auditing Inference-Time Defense Evaluation for Multimodal Large Language Models
Empirical comparison finds no single inference-time defense dominates for MLLMs, combinations cause 97-100% over-refusal on benign queries, and adaptive selection based on model and attack type is recommended.
-
Image-to-Video Diffusion: From Foundations to Open Frontiers
A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.