arXiv:2607. 05481v1 Announce Type: cross Abstract: Detection models running in adversarial environments face a malicious distribution that drifts rapidly while the benign distribution stays comparatively stable, so teams retrain and redeploy constantly to stay ahead of new threats.
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:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
The paper evaluates three AI model security scanners—ModelScan, ModelAudit, and Fickling—using a benchmark of 170 Pickle and PyTorch artifacts from 145 families, 135 of which have binary security labels. It distinguishes coverage metrics such as non‑N/A coverage, analysis completion, and definitive security decisions, finding that ModelAudit achieved 100% definitive decisions, Fickling 81.5%, and ModelScan 49.6%. When a definitive judgment was made, ModelScan reached perfect precision, recall, and F1, while Fickling added no unique true positives beyond those found by the other tools.
arXiv:2608. 10621v1 Announce Type: new Abstract: Recent research on Large Language Model (LLM) safety has widely adopted guardrails to identify unsafe LLM outputs.
arXiv:2606. 03523v1 Announce Type: cross Abstract: Early attribution of Advanced Persistent Threat (APT) activity can help defenders prioritise investigation, select countermeasures, and reduce the impact of an intrusion.
arXiv:2607. 17336v1 Announce Type: new Abstract: Drift detection is a core component of production machine learning monitoring systems, where detectors are used to compare incoming data with a reference distribution and trigger alerts when changes occur.
arXiv:2606. 31159v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do models know when their generated code is insecure?
arXiv:2606. 19023v1 Announce Type: cross Abstract: The growing reliance on pre-trained Machine Learning (ML) models has introduced new attack surfaces.
arXiv:2606. 05566v1 Announce Type: new Abstract: Large Language Models (LLMs) have transformed natural language processing, but they remain vulnerable to Prompt Injection (PI) and Jailbreak (JB) attacks.
The paper addresses the lack of statistical validity in language‑model‑based network intrusion detection. It introduces traffic‑aware conformal prediction, which calibrates on attacker‑expected traffic to restore coverage guarantees, and further mitigates adaptive attacks by removing attacker‑controllable features, achieving exact pathwise coverage. Experiments on three benchmarks show that this approach maintains coverage while incurring a modest accuracy cost.
arXiv:2609.40312v1 Announce Type: new Abstract: Lossy compression is widely used in Federated Learning (FL) but is generally treated as an error source, while conventional poisoning defenses inspect...
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.