REVIEW 12 cited by
MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
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
MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models
read the original abstract
The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models (MLLMs) can be easily compromised by query-relevant images, as if the text query itself were malicious. To address this, we introduce MM-SafetyBench, a comprehensive framework designed for conducting safety-critical evaluations of MLLMs against such image-based manipulations. We have compiled a dataset comprising 13 scenarios, resulting in a total of 5,040 text-image pairs. Our analysis across 12 state-of-the-art models reveals that MLLMs are susceptible to breaches instigated by our approach, even when the equipped LLMs have been safety-aligned. In response, we propose a straightforward yet effective prompting strategy to enhance the resilience of MLLMs against these types of attacks. Our work underscores the need for a concerted effort to strengthen and enhance the safety measures of open-source MLLMs against potential malicious exploits. The resource is available at https://github.com/isXinLiu/MM-SafetyBench
Forward citations
Cited by 12 Pith papers
-
Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
-
Multimodal Reward Hacking in Reinforcement Learning
Imperfect multimodal RL rewards systematically create new failures (NRFR > RHR); scaling and answer-aware rewards help but do not eliminate hacking, and unreliable visual verifiers actively increase it.
-
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
PolicyShiftGuard, trained with randomized policy SFT plus matched pass/block boundary pairs, reaches 76.9 Avg. F1 and 72.1 Avg. PSS on a new policy-shift image-guardrail benchmark where existing VLMs stay brittle.
-
Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models
A narrative survey that catalogs fifty papers on diffusion-based adversarial techniques across text, vision, and vision-language models, proposes a six-class taxonomy of diffusion roles plus a unified five-dimension e...
-
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.
-
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.
-
VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
Universal adversarial attacks cause output perturbation 90 times more often than precise target injection in VLMs, with only 2 verbatim successes out of 6615 tests.
-
AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis
AICA-Bench evaluates 23 VLMs on affective image analysis, identifies weak intensity calibration and shallow descriptions as limitations, and proposes training-free Grounded Affective Tree Prompting to improve performance.
-
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...
-
Calibrate Globally, Measure Everywhere: Scaling LLM-Based Prevalence Measurement Across A/B Experiments
A reusable score-bucket calibration replaces per-experiment LLM labeling, giving daily per-arm content-prevalence estimates from impression logs at a fraction of the cost.
-
Robust and Generalizable Safety Steering for Text-to-Image Diffusion Transformers
SafeDIG applies position-aware sparse feature transfer via SAEs in DiT models to reduce unsafe generations in target risk domains on FLUX.1 Dev and SD 3.5 while keeping source safety and quality.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.