arXiv:2611.11266v1 Announce Type: new Abstract: As enterprises delegate consequential work to multi-agent LLM systems, benign-looking requests can escalate into unsafe actions as they propagate across sessions through poisoned shared state, long-context documents, and trusted pe…
⏱ Độ trễ thật của tab này: trung bình 7.2 giờ sau khi CVE được công bố (n = 5386, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.15223v1 Announce Type: new Abstract: Large-language model (LLM) agents execute actions on external systems through tool calls, and enterprises deploy runtime controls, such as agent gateways, to check this behavior in real time. However, a control can only evaluate th…
arXiv:2611.15097v1 Announce Type: new Abstract: Web agents need to use private context without unnecessarily disclosing it. Effective protection must distinguish between requests that may be sent after sanitization and those that must be withheld, while preserving the informatio…
arXiv:2611.13006v1 Announce Type: new Abstract: Medical vision-language models (VLMs) often report a finding because the question names it; standard benchmarks miss this. From public segmentation datasets we build counterfactual views without manual annotation: the lesion erased…
arXiv:2611.12935v1 Announce Type: new Abstract: Topic monitoring is the task of labelling the topic of each token in a model's response during generation. Activation-based monitors that run at generation time have so far been trained to detect harmful content and are limited to …
arXiv:2611.12940v1 Announce Type: new Abstract: Reinforcement Learning has achieved tremendous success in recent years. Extending its scope from the traditional complex games such as Atari, Go, Pokeman, and Chess, reinforcement learning has caught researchers' attention on model…
arXiv:2611.13232v1 Announce Type: new Abstract: We present W-ISA, a software instruction set and transactional runtime for executing weight-space intervention programs on pretrained language models. Shape-checked instructions express parameter updates, projections, ablations, an…
arXiv:2611.10030v1 Announce Type: new Abstract: This technical report describes an alignment investigation into Mythos 5's behaviour during a security incident in UK AISI's cyber evaluations. During an evaluation, Mythos 5 attempted to execute a supply-chain attack against real …