arXiv Machine Learning July 24, 2026 By Muntasir Adnan, Manile Srun, Carlos C. N. Kuhn

From Evaluation to Optimisation: Hierarchy-Aware Training Signals for CWE Prediction in Python

Read the original on arXiv Machine Learning →

arXiv:2607. 21069v1 Announce Type: new Abstract: The original ALPHA benchmark introduced a taxonomy-aware penalty for evaluating CWE-level vulnerability prediction in Python and proposed that the penalty could theoretically also serve as a training signal.

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

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

Jul 24

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

arXiv:2603. 13026v2 Announce Type: replace Abstract: Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents.

By Chenlong Yin, Runpeng Geng, Yanting Wang, Jinyuan Jia

llms agents reinforcement-learning efficiency benchmarks safety

arXiv AI

Aug 6

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning

arXiv:2608. 05045v1 Announce Type: cross Abstract: Released aligned large language models remain vulnerable to malicious downstream finetuning.

By Yuxuan Huang, Xingyu Zeng, Tianhang Zheng, Chaochao Lu

llms fine-tuning 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

Jul 16

UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors

arXiv:2607. 13565v1 Announce Type: cross Abstract: We investigate which language model evasion attacks survive state-of-the-art adversarial fine-tuning, developing strategies that sweep the top 5 positions on the ELOQUENT 2026 Voight-Kampff leaderboard.

By Dima Galat, Marian-Andrei Rizoiu

llms fine-tuning benchmarks safety

arXiv AI

Jun 16

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment

arXiv:2606. 15441v1 Announce Type: cross Abstract: Indirect prompt injection attacks hijack LLM-based agents by embedding malicious instructions in third-party data that the agent retrieves during task execution.

By Lipeng He, Yihan Wang, Jiawen Zhang, N. Asokan

llms rag agents reinforcement-learning multimodal benchmarks safety

Related stories

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

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning

Quality-Diversity Evolution for Discovering Diverse Vulnerabilities in LLM Safety

UTS at ELOQUENT 2026 Voight-Kampff: structural shifts in AI writing bypass state-of-the-art detectors

Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment