arXiv AI

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B

arXiv:2607. 22545v1 Announce Type: cross Abstract: Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single inference pass.

arXiv Machine Learning

Jul 7

ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems

arXiv:2604. 11943v3 Announce Type: replace-cross Abstract: An OS kernel that runs LLM inference internally can read the model's own next-token logit distribution before any text is generated, and act on it as a governance primitive.

By Daeyeon Son

llms agents fine-tuning benchmarks safety

arXiv AI

Jul 15

Silent Alarm: A J-Space Protocol for Comparing Danger Recognition Across Models and Quantization Levels

arXiv:2607. 12792v1 Announce Type: cross Abstract: Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach.

By Roman Prosvirnin, Victor Minchenkov, Alexey Soldatov, Vladimir Bashun

llms fine-tuning efficiency benchmarks safety

arXiv AI

Jul 3

Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment

arXiv:2607. 01239v1 Announce Type: cross Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable.

By Tung-Ling Li, Hongliang Liu, Yuhao Wu

llms nlp reinforcement-learning fine-tuning multimodal safety

arXiv AI

Jun 3

Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing

arXiv:2606. 02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet existing breach-and-attack-simulation (BAS) benchmarks report a single aggregate coverage number, hiding which family closes which threat.

By Alexandre Cristov\~ao Maiorano

llms agents benchmarks safety

arXiv Machine Learning

Jun 3

Gate AI: LLM Security Benchmark Evaluation Methodology and Results

arXiv:2606. 02959v1 Announce Type: new Abstract: Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points.

By Ryle Goehausen, Marcus Sousa

llms benchmarks safety

arXiv AI

Aug 11

Do All LLMs Know When They're Being Harmful? A Reproducibility Study of Latent-Space Safety Probes Across Model Families

arXiv:2608. 08029v1 Announce Type: cross Abstract: Khatri et al.

By Alizishaan Khatri, Dun Li Chan

llms benchmarks safety

arXiv AI

Aug 5

Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity

arXiv:2608. 02665v1 Announce Type: cross Abstract: A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form.

By Yongxi Zhou, Junwei Yao, Yuanzhe Liu, Zihan Dong, Wenbo Ye, Jiaxi Wen, Lai Yun Choi

llms benchmarks safety

arXiv AI

Jun 16

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

arXiv:2606. 15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted.

By Ismail Hossain, Sai Puppala, Md Jahangir Alam, Tanzim Ahad, Sajedul Talukder

llms agents benchmarks

arXiv AI

Jul 7

A Failure-Mode Benchmark for Polymorphic Sybil Poisoning in RAG

arXiv:2607. 03739v1 Announce Type: cross Abstract: We release a benchmark and failure-mode-aware evaluation framework for grounded QA under coordinated retrieval poisoning.

By Donghyun Lee (Dongguk University), Juntae Kim (Dongguk University)

rag multimodal benchmarks

arXiv Machine Learning

Jul 21

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

arXiv:2602. 14161v2 Announce Type: replace Abstract: Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization.

By Max Fomin

llms agents benchmarks safety

arXiv Machine Learning

Jun 11

Online Shift Detection and Conformal Adaptation for Deployed Safety Classifiers

arXiv:2606. 11949v1 Announce Type: new Abstract: We present an online monitoring system for distributional shift in deployed safety classifiers, using calibrated sequential statistics to detect when a classifier has moved out of distribution.

By Jun Wen Leong

llms rag safety

arXiv AI

2d ago

A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation

arXiv:2608. 14329v1 Announce Type: cross Abstract: Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge is increasingly used as the substitute.

By Dipankar Sarkar

llms benchmarks safety

Related stories