arXiv Machine Learning August 14, 2026 By Zhenpeng Li

Non-Degenerate Risk Certification for Automated Security Decisions: A Decision-Contract Theory with ATT\&CK-Aligned Triage as a Worked Instance

Read the original on arXiv Machine Learning →

arXiv:2608. 12444v1 Announce Type: cross Abstract: An unconditional risk bound on automated decisions can be satisfied without automating anything, since a selector that never acts drives the bound to zero.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

llms

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.

By Su Wang, Pin Qian, Yihang Chen, Junxian You, Xiaoyuan Wang, Xiaochong Jiang, Lifei Liu, Haoran Yu, Jingzhou Xu

llms agents benchmarks safety

arXiv AI

Jul 8

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

arXiv:2607. 05842v1 Announce Type: cross Abstract: Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair can closely resemble terminology associated with misuse.

By Mingchen Li, Meikang Qiu, Zifan Peng, Heng Fan, Song Fu, Junhua Ding, Yunhe Feng

llms safety

arXiv AI

Jul 28

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI

arXiv:2607. 22926v1 Announce Type: new Abstract: High-impact generative AI makes catastrophic misuse a lifecycle-control problem, not merely a prompt-filtering problem.

By Mahdi Eslamimehr

llms safety

arXiv AI

Jun 6

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

arXiv:2606. 05396v1 Announce Type: cross Abstract: Producing a labeled vulnerable code at scale is a recurring obstacle for learning-based vulnerability detection: mined corpora carry substantial label noise, and existing LLM-based augmentation propagates these inaccuracies because it transforms vulnerable seeds rather than synthesising vulnerabilities from a specification.

By Cristina Carleo, Pietro Liguori, Naghmeh Ivaki, Domenico Cotroneo

llms reinforcement-learning safety data-engineering

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.

By Vadym Hadetskyi, Dario Pasquini, Artem Sorokin

llms safety

arXiv AI

Jun 19

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software

arXiv:2606. 20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved.

By Arastoo Zibaeirad, Marco Vieira

llms fine-tuning benchmarks

Related stories

When Safe Skills Collide: Measuring Compositional Risk in Agent Skill Ecosystems

Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis

SAGE: Safety-First Defense-in-Depth Guardrails for Verified Lifecycle Control of High-Impact Generative AI

Willing but Unable: Separating Refusal from Capability in Code LLMs via Abliteration

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software