Red Teaming Multimodal Language Models: Evaluating Harm Across Prompt Modalities and Models
Multimodal large language models (MLLMs) are increasingly used in real world applications, yet their safety under adversarial conditions remains underexplored. This study evaluates the harmlessness of four leading MLLMs (GPT-4o, Claude Sonnet 3.5, Pixtral 12B, and Qwen VL Plus) when exposed to adversarial prompts across text-only and multimodal formats. A team of 26 red teamers generated 726 prompts targeting three harm categories: illegal activity, disinformation, and unethical behaviour. These prompts were submitted to each model, and 17 annotators rated 2,904 model outputs for harmfulness using a 5-point scale. Results show significant differences in vulnerability across models and modalities. Pixtral 12B exhibited the highest rate of harmful responses (~62%), while Claude Sonnet 3.5 was the most resistant (~10%). Contrary to expectations, text-only prompts were slightly more effective at bypassing safety mechanisms than multimodal ones. Statistical analysis confirmed that both model type and input modality were significant predictors of harmfulness. These findings underscore the urgent need for robust, multimodal safety benchmarks as MLLMs are deployed more widely.
Code (0)
등록된 구현이 없습니다.
Tasks
Red TeamingSimilar Papers 제목 키워드 기반
Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks
Vision-Language Models (VLMs) with multimodal reasoning capabilities are high-value attack targets, given their potential for handling complex multimodal harmful tasks. Mainstream black-box jailbreak attacks on VLMs work…
Multimodal ReasoningARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks
As vision-language models (VLMs) gain prominence, their multimodal interfaces also introduce new safety vulnerabilities, making the safety evaluation challenging and critical. Existing red-teaming efforts are either rest…
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigoro…
Red TeamingVisual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning
Current multimodal red teaming treats images as wrappers for malicious payloads via typography or adversarial noise. These attacks are structurally brittle, as standard defenses neutralize them once the payload is expose…
Red TeamingAgainst The Achilles' Heel: A Survey on Red Teaming for Generative Models
Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed. In light of this, the field of red teaming is…
Red TeamingSurvey