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 7.3 giờ sau khi CVE được công bố (n = 5335, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.17395v1 Announce Type: new Abstract: Recent advances in weight-space programming (WSP) have demonstrated that large language models (LLMs) can directly inspect and modify neural network weights without conventional gradient-based training. While this capability opens …
arXiv:2611.10026v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility cou…
arXiv:2611.11305v1 Announce Type: new Abstract: LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph fro…
arXiv:2611.16122v1 Announce Type: new Abstract: AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily detect prompt injection, harmful outputs, or suspicious behavior, but do not determine…
arXiv:2611.16693v1 Announce Type: new Abstract: Mobile GUI agents read the screen of a phone and operate apps on a user's behalf to complete multi-step tasks such as online shopping or messaging. Because the agent acts on whatever the screen shows, an attacker can embed maliciou…
arXiv:2611.16151v1 Announce Type: new Abstract: Hardware fault injection attacks threaten machine learning systems, yet their impact on reinforcement learning (RL) has received little attention despite the use of RL in safety-critical applications. This paper presents a security…
arXiv:2611.10099v1 Announce Type: new Abstract: We study a safety harness that improves itself without touching model weights. Enmo Safety wraps a chat model with a deterministic input assessment, trigger-matched safety guidance, spotlighting of untrusted content, and an output …
arXiv:2611.11172v1 Announce Type: new Abstract: Although hidden-state probes efficiently monitor model operation, it remains unclear whether probes trained on benign tool use remain useful for detecting incorrect actions under adversarial conditions. In this research, we assess …