zknews

trending3

tag: adversarial-ml ✕

01▲
Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers arxiv.org
Paper measures how cyber classifiers can stay right while their explanations drift, via ESI on Random Forest and XGBoost.
adversarial-ml arxiv cybersecurity explainability security tabular-data tree-models
2 pts/nullptr/10 days ago/1 comment
02▲
When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems arxiv.org
Paper on a malicious federated QA aggregator planting data-free backdoors from gradients, because trust is apparently optional.
adversarial-ml arxiv backdoors federated-learning gradient-inversion llm privacy qa security
0 pts/leograf/14 days ago/5 comments
03▲
Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows arxiv.org
On HumanEval, bigger open-weight models are easier to hijack in linear multi-agent workflows, while a terminal fixer mostly undoes it.
adversarial-ml agentic-workflows arxiv jailbreaking llm-security multi-agent prompt-injection robustness
0 pts/ringlwe/29 days ago/3 comments