Charles Maalouf

Kundan Krishna, Joseph Y Cheng, Charles Maalouf et al.

Existing paradigms for ensuring AI safety, such as guardrail models and alignment training, often compromise either inference efficiency or development flexibility. We introduce Disentangled Safety Adapters (DSA), a novel framework addressing these challenges by decoupling safety-specific computations from a task-optimized base model. DSA utilizes lightweight adapters that leverage the base model's internal representations, enabling diverse and flexible safety functionalities with minimal impact on inference cost. Empirically, DSA-based safety guardrails substantially outperform comparably sized standalone models, notably improving hallucination detection (0.88 vs. 0.61 AUC on Summedits) and also excelling at classifying hate speech (0.98 vs. 0.92 on ToxiGen) and unsafe model inputs and responses (0.93 vs. 0.90 on AEGIS2.0 & BeaverTails). Furthermore, DSA-based safety alignment allows dynamic, inference-time adjustment of alignment strength and a fine-grained trade-off between instruction following performance and model safety. Importantly, combining the DSA safety guardrail with DSA safety alignment facilitates context-dependent alignment strength, boosting safety on StrongReject by 93% while maintaining 98% performance on MTBench -- a total reduction in alignment tax of 8 percentage points compared to standard safety alignment fine-tuning. Overall, DSA presents a promising path towards more modular, efficient, and adaptable AI safety and alignment.

Shruti Palaskar, Leon Gatys, Mona Abdelrahman et al.

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish clearly unsafe content from borderline cases, leading to problematic over-blocking or under-refusal of genuinely harmful content. We present Vision Language Safety Understanding (VLSU), a comprehensive framework to systematically evaluate multimodal safety through fine-grained severity classification and combinatorial analysis across 17 distinct safety patterns. Using a multi-stage pipeline with real-world images and human annotation, we construct a large-scale benchmark of 8,187 samples spanning 15 harm categories. Our evaluation of eleven state-of-the-art models reveals systematic joint understanding failures: while models achieve 90%-plus accuracy on clear unimodal safety signals, performance degrades substantially to 20-55% when joint image-text reasoning is required to determine the safety label. Most critically, 34% of errors in joint image-text safety classification occur despite correct classification of the individual modalities, further demonstrating absent compositional reasoning capabilities. Additionally, we find that models struggle to balance refusing unsafe content while still responding to borderline cases that deserve engagement. For example, we find that instruction framing can reduce the over-blocking rate on borderline content from 62.4% to 10.4% in Gemini-1.5, but only at the cost of under-refusing on unsafe content with refusal rate dropping from 90.8% to 53.9%. Overall, our framework exposes weaknesses in joint image-text understanding and alignment gaps in current models, and provides a critical test bed to enable the next milestones in research on robust vision-language safety.