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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. 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 Machine Learning

Aug 31

RiskBlend: A Multi-Signal Framework for Test Input Prioritization in Machine Learning Regression Testing

arXiv:2608.27704v1 Announce Type: new Abstract: When machine learning classifiers are retrained, inputs correctly classified by the previous model version may be misclassified by the updated version,...

By Madhusudan Srinivasan, Namith Nishal Raphae

arXiv Computer Vision

3d ago

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

arXiv:2605.25663v2 Announce Type: replace-cross Abstract: Black-box adversarial attacks that minimize only the ground-truth confidence suffer from class drift: perturbations wander through the featur...

By Florent Tariolle, Florian Yger

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

Sep 10

WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents

arXiv:2605.23220v2 Announce Type: replace Abstract: Despite the growing use of world models as decision-making agents, their adversarial robustness remains underexplored due to the lack of dedicated...

By Zhixiang Guo, Siyuan Liang, Shi Fu, Cheng Guo, Andras Balogh, Mark Jelasity, Dacheng Tao

agents safety

One email a morning, machine-written

Related stories

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

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

RiskBlend: A Multi-Signal Framework for Test Input Prioritization in Machine Learning Regression Testing

Opportunistic Target Selection: Early Directional Commitment for Query-Efficient Black-Box Adversarial Attacks

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

WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agents