arXiv:2608. 19901v1 Announce Type: cross Abstract: Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration.
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. 18530v1 Announce Type: cross Abstract: Domain-camouflaged injection attacks embed malicious instructions in retrieved content using domain-appropriate vocabulary, evading standard detectors that rely on syntactic injection markers.
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
arXiv:2608. 08027v1 Announce Type: cross Abstract: Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data.
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:2606.17467v3 Announce Type: replace-cross Abstract: Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and int...
arXiv:2608. 01454v1 Announce Type: cross Abstract: Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols.
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.
The paper introduces the Latent Diagnostic Taxonomy, a framework that builds a dimensionality‑optimized classifier and a diagnostic tool to assess the trustworthiness of its confident predictions. It identifies a small set of influential prompts (latent support vectors) that reveal tokens which can change the classifier’s output, and uses these tokens to create a taxonomy that classifies prompts into safe, heuristic bias, heuristic override, or insufficient context categories. Applied to a prompt‑injection detection model, the framework shows that about 77% of confident decisions are fragile to a single token, distinguishing between calibration failures and exploitable shortcuts, and offers remediation strategies for each taxonomy zone.
arXiv:2608.21230v1 Announce Type: cross Abstract: Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future sessions that match it. We measu...
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.