Activation steering offers an inference-time defense for vision--language models (VLMs) by modifying intermediate representations without updating backbone parameters. However, protection on benchmark inputs may not persist across alternative expressions of the same harmful request. We investigate this gap using fixed …
As GUI-based mobile agents rapidly progress, rigorous safety evaluation of their autonomous decision-making in realistic app interfaces becomes increasingly critical. Existing benchmarks mainly focus on execution-level anomalies using task success or hijack rates, but fail to capture the in-task goal deviation risk in …
Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that task-, attack-, or choice-based evaluations may miss. We study functional counterfeits: implementations that match benign alternatives on the …
Machine unlearning aims to remove target influence while preserving other capabilities. This survey compares methods, benchmarks, and evidence across large language models and systems using retrieval, memory, tools, and interacting agents. A five-layer framework connects removal requests, system boundaries, target loca …
Text-to-image diffusion models enable data-efficient "mimicry" attacks, wherein adversaries fine-tune the model on a handful of public photos to synthesize convincing forgeries of a target individual. A common countermeasure is to embed imperceptible, low-energy watermarks, yet recent studies show these signatures are …
Multimodal training relies on image-text corpora collected from external sources, creating opportunities for attackers to poison the data. Stealthy attacks can preserve plausible image-text pairs while concealing the differences used by detectors, so apparently clean data can still redirect the trained model. We theref …