5 papers
Detecting Adversarial Images through Response Profiles of Vision-Language Models
Arash Vashagh, Roozbeh Razavi-Far
Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible.…
GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural Networks
Arash Vashagh, Roozbeh Razavi-Far
Adversarial example detectors are often tied to the classifier backbone they were trained on, limiting reuse when the protected model is replaced or upgraded. Directly transferring…
ChronosAttack: Adversarial Tool Scheduling Attacks on LLM Agents
Arash Vashagh
Large language model (LLM) agents often process external tool responses as they arrive, making response timing part of the decision process. We introduce ChronosAttack, a delay-onl…
CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal
Arash Vashagh, Yasmin Vashagh
Many single-cell annotation tools refine an initial cell label using nearby cells or cluster-level voting. We study whether this refinement can be manipulated without changing the…
ConformalShift: Targeted Event Reordering Against Adaptive ECG Monitoring
Arash Vashagh, Yasmin Vashagh
Adaptive conformal prediction can recover clinically important heartbeat classes missed by a point classifier, but delayed feedback makes its decisions sensitive to event order. We…