arXiv AI
Jul 7
Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale
arXiv:2607. 02714v1 Announce Type: cross Abstract: There is no doubt that safety alignment is an essential step in LLM training.
FUSE: An Evaluating Framework for Dangerous Capabilities of LLMs
The paper introduces FUSE, a modular framework that evaluates large language models (LLMs) for dangerous capabilities across three orthogonal pipelines: Knowledge (K), Defense (D), and Harm (H). Using a chemical‑biological module, the authors assess 12 commercial LLMs, revealing divergent profiles among models and families, and showing that newer models increase knowledge while only partially improving defense. The framework’s reliability is supported by high cross‑judge consistency and low inter‑pipeline correlations.
Related stories
arXiv AI
3d ago
Artificial intelligence and biosecurity: capabilities, threat pathways, and defense-in-depth governance
arXiv:2609.16213v1 Announce Type: new Abstract: Artificial intelligence is reshaping biological research across an increasingly connected digital-to-physical workflow. General-purpose large language...
arXiv AI
Jun 2
When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems
arXiv:2606. 00448v1 Announce Type: cross Abstract: LLM agents increasingly rely on community-contributed skills that expand an agent's operational capability set.
arXiv AI
Jun 4
Unpredictable Safety: Domain-Dependent Compliance and the Transparency Gap in Open-Weight LLMs
arXiv:2606. 04035v1 Announce Type: cross Abstract: We present a systematic study of domain-dependent safety behavior in open-weight LLMs: 7 standardized experiments across 7 ethical domains, testing 5 models (12B--70B) in 4,200 interactions with dual-judge validation.
arXiv Machine Learning
Aug 11
When Skills Meet Safety: Benchmarking and Characterizing the Adaptive Jailbreak Robustness of Skill-Merged LLMs
arXiv:2608. 08542v1 Announce Type: new Abstract: Model merging has become the default way to give an aligned language model new skills without retraining: a practitioner folds task vectors from math, code, or domain specialists into a safety-aligned base using task arithmetic, TIES, or DARE.
arXiv AI
Jun 12
Muse Spark Safety & Preparedness Report
arXiv:2606. 12429v1 Announce Type: cross Abstract: Muse Spark is the latest large language model developed by Meta.
arXiv AI
Jun 6
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
arXiv:2606. 05614v1 Announce Type: new Abstract: Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content.
arXiv AI
Jul 22
The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
arXiv:2607. 19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios.
arXiv AI
Jul 2
From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems
arXiv:2410. 22526v2 Announce Type: replace Abstract: To effectively address potential harms from Artificial Intelligence (AI) systems, it is essential to identify and mitigate system-level hazards.
arXiv AI
Jun 19
LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems
arXiv:2606. 20408v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized.
arXiv AI
Jun 2
The Refusal--Compliance Tradeoff: A Large-Scale Safety Behavior Audit of Large Language Models
arXiv:2605. 05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.
arXiv AI
Jun 4
Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety
arXiv:2603. 10044v2 Announce Type: replace-cross Abstract: A safety score earned on a benchmark need not predict how the same model behaves once it is wrapped in an agentic scaffold the benchmark never tested.