arXiv AI

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.

arXiv AI

Jul 7

JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation Mode

arXiv:2607. 02825v1 Announce Type: cross Abstract: We release \textsc{JavaVulBench}, a benchmark dataset and evaluation harness for Java vulnerability detection.

By Norbert Sandor Szolnoki, Gabor Antal

llms fine-tuning benchmarks

arXiv AI

Jun 26

Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

arXiv:2606. 27091v1 Announce Type: cross Abstract: LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data.

By Ryan Fetterman

llms fine-tuning 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 2

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

arXiv:2606. 00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not scale, LLM-as-attacker methods exhibit mode collapse, and gradient-based approaches produce uninterpretable gibberish.

By Subhadip Mitra

llms safety

arXiv AI

Jun 3

FORGE: Multi-Agent Graduated Exploitation and Detection Engineering

arXiv:2606. 03453v1 Announce Type: cross Abstract: Vulnerability disclosure volumes now far exceed organizational assessment capacity, yet three adjacent research communities (proof-of-concept generation, vulnerability prioritization, and detection rule engineering) operate largely in isolation.

By Farooq Shaikh

llms agents

arXiv AI

Jun 4

TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering

arXiv:2602. 06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving their tamper resistance against unsafe modifications, whether accidental or intentional, becomes critical to minimize risks.

By Saad Hossain, Tom Tseng, Punya Syon Pandey, Samanvay Vajpayee, Matthew Kowal, Nayeema Nonta, Samuel Simko, Stephen Casper, Zhijing Jin, Kellin Pelrine, Sirisha Rambhatla

llms fine-tuning 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

Jun 11

Are Frontier LLMs Ready for Cybersecurity? Evidence for Vertical Foundation Models from Dual-Mode Vulnerability Benchmarks

arXiv:2605. 23243v2 Announce Type: replace-cross Abstract: We evaluate whether frontier LLMs are ready for cybersecurity through a dual-mode benchmark: white-box function-level vulnerability detection (VulnLLM-R, across C/Java/Python) and black-box web application security testing (five production-style applications with 118 ground-truth vulnerabilities across 20+ CWE families, which we will open-source).

By Vivek Dahiya, Sunny Nehra, Vipul Dholariya, Bhavik Shangari, Chandra Khatri

llms agents reinforcement-learning benchmarks

arXiv AI

Aug 11

SALLIE: Generation-Free Hidden-State Detection of Jailbreaks and Prompt Injections Across Text and Vision

arXiv:2604. 06247v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are vulnerable to jailbreaks and prompt injections delivered through text or images.

By Guy Azov, Ofer Rivlin, Guy Shtar

llms multimodal

arXiv AI

Jun 2

Needles at Scale: LLM-Assisted Target Selection for Windows Vulnerability Research

arXiv:2606. 01364v1 Announce Type: cross Abstract: The attack surface of a modern operating system is a haystack: thousands of signed binaries and millions of functions, almost none relevant to any given vulnerability.

By Michael J. Bommarito II

llms agents

arXiv Machine Learning

Jul 3

From Lab to Reality: A Practical Evaluation of Deep Learning Models and LLMs for Vulnerability Detection

arXiv:2512. 10485v2 Announce Type: replace-cross Abstract: Vulnerability detection methods based on deep learning (DL) have shown strong performance on benchmark datasets, yet their real-world effectiveness remains underexplored.

By Chaomeng Lu, Bert Lagaisse

llms benchmarks

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

Related stories