REVIEW 12 cited by
Multimodal Situational Safety
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
Multimodal Large Language Models (MLLMs) are rapidly evolving, demonstrating impressive capabilities as multimodal assistants that interact with both humans and their environments. However, this increased sophistication introduces significant safety concerns. In this paper, we present the first evaluation and analysis of a novel safety challenge termed Multimodal Situational Safety, which explores how safety considerations vary based on the specific situation in which the user or agent is engaged. We argue that for an MLLM to respond safely, whether through language or action, it often needs to assess the safety implications of a language query within its corresponding visual context. To evaluate this capability, we develop the Multimodal Situational Safety benchmark (MSSBench) to assess the situational safety performance of current MLLMs. The dataset comprises 1,820 language query-image pairs, half of which the image context is safe, and the other half is unsafe. We also develop an evaluation framework that analyzes key safety aspects, including explicit safety reasoning, visual understanding, and, crucially, situational safety reasoning. Our findings reveal that current MLLMs struggle with this nuanced safety problem in the instruction-following setting and struggle to tackle these situational safety challenges all at once, highlighting a key area for future research. Furthermore, we develop multi-agent pipelines to coordinately solve safety challenges, which shows consistent improvement in safety over the original MLLM response. Code and data: mssbench.github.io.
Forward citations
Cited by 12 Pith papers
-
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models
The authors release a large multimodal benchmark showing that current LMMs struggle to detect toxicity that emerges only from combining image and text, and that many-shot toxic demonstrations further reduce their accuracy.
-
SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\circ}$ Law
SafeWork-R1 shows that a staged RL pipeline with safety, value, and knowledge verifiers can improve both safety and general reasoning scores over a base multimodal model.
-
USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models
USB-SafeBench is a unified MLLM safety benchmark with 61 risk categories, 4 modality combinations, and dual-language vulnerability and oversensitivity tests.
-
ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
ShieldVLM detects multimodal implicit toxicity through deliberate cross-modal reasoning, outperforming existing moderation APIs and models on the new MMIT benchmark.
-
How Jailbreak Attacks Inform Safety Alignment: A Defender-Centric, Shapley-Based Evaluation of Jailbreak Contributions
Attacks that break LLMs best are not the ones that improve safety most; a Shapley- and greedy-based framework that selects attack subsets by downstream defender utility outperforms attacker-centric and attribution-onl...
-
Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
A new step-level reward-modeling benchmark for multimodal agents shows current MLLMs reach at most 61.6 percent accuracy, and benchmark score correlates strongly (r=0.981 across five models) with downstream A* search ...
-
SafeCoT: Improving VLM Safety with Minimal Reasoning
Training vision-language models to emit a short rule-based reasoning chain before refusing improves the safety-usefulness balance, with reported gains even at 100 training samples.
-
Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures
JailFlipBench and JailFlip attacks show that leading LLMs can be made to answer benign-looking questions with plausible but factually wrong and dangerous responses.
-
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
A two-stage evaluation framework and token-projection analysis show that LVLMs encode harmful semantic cues from images even without OCR, while remaining vulnerable to cross-modal attacks.
-
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
A new benchmark, VSCBench, measures oversafety and undersafety in vision-language models and shows that most models, including proprietary ones, are miscalibrated on at least one safety dimension.
-
Generative RLHF-V: Learning Principles from Multi-modal Human Preference
A reinforcement-learned multimodal judge with grouped pairwise scoring improves vision-language model alignment on seven benchmarks.
-
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.