arXiv:2607. 24896v1 Announce Type: cross Abstract: Static malware detectors are commonly evaluated using clean-sample metrics such as accuracy, F1, ROC AUC, and PR AUC.
arXiv:2606. 30572v1 Announce Type: cross Abstract: Malware classification remains a challenging problem due to its inherent heterogeneity, the presence of packed binaries, and the diverse distribution of malware families.
arXiv:2608. 13465v1 Announce Type: cross Abstract: Concept drift refers to changes over time in the statistical properties of data, as compared to the data that was used to train a learning model.
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.
arXiv:2606. 07963v1 Announce Type: new Abstract: Backdoor attacks in large language models (LLMs) are often treated as isolated trigger-response failures, motivating defenses tailored to specific triggers or behaviors.
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:2604. 23130v2 Announce Type: replace-cross Abstract: Jailbreak attacks expose a persistent failure mode in safety-aligned LLMs: models can be pushed into harmful behavior, but the internal representations enabling this shift remain poorly localized.
arXiv:2607. 19894v1 Announce Type: cross Abstract: Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs.
arXiv:2606. 20436v1 Announce Type: cross Abstract: Malware analysts often inspect compiled binaries through decompiled pseudo-C, when source code is unavailable.
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.
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.
Large language models (LLMs) are vulnerable to backdoor attacks, where hidden triggers induce malicious outputs. Existing defenses generally fall into inference-time detection or training-time mitigation, but face two key limitations.
arXiv:2607. 00958v1 Announce Type: new Abstract: Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances.