When an LLM group's discussion is compressed into a short memory for a final decision maker, what should the memory keep? Two natural heuristics keep the rarest claims or the claims relevant to the decision criteria. On hidden-profile tasks both look attractive, because how widel…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5436, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2610.37989v1 Announce Type: new Abstract: Large language model (LLM) inference has become an operational workload that fleets must provision, monitor, and bill against latency service-level objectives (SLOs). A single throughput number cannot answer the questions operators…
arXiv:2610.38210v1 Announce Type: new Abstract: Weight-only, lossy quantization substantially reduces the storage and memory requirements for serving large language models (LLMs), but the growing key-value (KV) cache remains a bottleneck for long-context inference on personal de…
arXiv:2610.38220v1 Announce Type: new Abstract: Rubrics enable reward assignment on tasks without verifiable answers, but are expensive to manually produce from scratch. We present Rubricon, a pipeline that generates discriminative rubrics without requiring human preference labe…
arXiv:2610.37716v1 Announce Type: new Abstract: Attribute-Based Access Control (ABAC) policy mining---recovering a compact, auditable policy from an access log---is posed as minimum set cover and solved greedily, which enjoys an $s^{*}(1+\ln m)$ guarantee. That guarantee is \emp…
arXiv:2610.37797v1 Announce Type: new Abstract: Software vulnerability detection remains difficult because existing approaches rely on predefined analysis rules, learn vulnerability patterns implicitly from code and labels, or use large language models (LLMs) to make the final s…
arXiv:2610.37949v1 Announce Type: new Abstract: AI-generated non-consensual intimate imagery (AIG-NCII) is an increasingly prevalent form of online abuse, distinguished from AI-generated sexual content (AIG-SC) by the sexualized depiction of a real person's identity without thei…
arXiv:2610.38126v1 Announce Type: new Abstract: Web assistants increasingly answer questions about a user's private documents by pairing a small on-device model with a cloud LLM behind a Web API. In collaborative decoding, the document stays on the client, and the cloud receives…
arXiv:2610.38524v1 Announce Type: new Abstract: Large language models (LLMs) have enabled more effective vulnerability scanning of web applications. However, these capabilities also make it significantly easier for attackers to automate cyberattacks on the web. In this work, we …
arXiv:2610.38945v1 Announce Type: new Abstract: Optimal power flow (OPF) is a foundational analysis in power system operation, and inaccuracies in OPF decision-making can result in significant operational and security consequences. With the increasing adoption of machine-learnin…
arXiv:2610.39066v1 Announce Type: new Abstract: Automatically validating AI-generated security patches remains a significant challenge. Eliminating a reported crash and passing existing test suites do not provide sufficient confidence that a patch correctly addresses the underly…
arXiv:2610.39155v1 Announce Type: new Abstract: Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Appl…
arXiv:2610.40890v1 Announce Type: new Abstract: Large language models (LLMs) can generate detailed guidance, functional code, and persuasive text at scale. As one of the most widely used consumer language model products as of 2026, ChatGPT gives broad public access to these capa…
arXiv:2610.40992v1 Announce Type: new Abstract: Managing multiple chronic conditions through diet requires satisfying disease- and medication-specific requirements jointly across meals and days while preserving established eating habits. These requirements are public in clinical…
arXiv:2610.41165v1 Announce Type: new Abstract: Large Language Models (LLMs) can generate toxic content, motivating effective test-time detoxification. Existing representation steering methods often rely on static or coarse interventions and provide imprecise guidance because th…
arXiv:2610.41232v1 Announce Type: new Abstract: As Large Language Models (LLMs) become increasingly multilingual, distinguishing human-written from AI-generated text is essential for maintaining information integrity. However, research remains English-centric, with limited bench…
arXiv:2610.40928v1 Announce Type: new Abstract: The omission of source IP authentication remains a fundamental vulnerability in the Internet. Existing approaches rely on routing plausibility, topology assumptions, per-flow state, or wide deployment. These requirements have kept …
arXiv:2610.41083v1 Announce Type: new Abstract: Untrusted third-party entities throughout the semiconductor supply chain expose proprietary hardware intellectual property to reverse engineering, piracy, and overproduction. While logic locking counters this threat by embedding ke…
arXiv:2610.41191v1 Announce Type: new Abstract: LLM agents increasingly triage security alerts by combining the outputs of several detection tools, implicitly treating those tools as trustworthy. Unlike prior work on conflicts between a model's knowledge and its context, we stud…
arXiv:2610.41713v1 Announce Type: new Abstract: AI control relies on monitors to catch a capable model that sabotages its work. These monitors are evaluated on their ability to differentiate honest from backdoored code. We show that on a standard evaluation dataset, simple featu…
arXiv:2610.41803v1 Announce Type: new Abstract: Detectors can flag hijacked large language model (LLM) agents from the traces of the tools they call. In the eleven evaluations we audited, attacks or anomalies make up 16% to 86% of the test samples, no evaluation varies that shar…
arXiv:2610.42032v1 Announce Type: new Abstract: The Internet of Things (IoT) has expanded beyond consumer smart homes to sectors, such as industrial systems, healthcare, and smart cities, broadening the IoT attack surface. Prior empirical work has focused on studying aggregate I…
arXiv:2610.41039v1 Announce Type: cross Abstract: As Mixture-of-Experts (MoE) large language models are increasingly deployed in distributed environments, from federated learning to edge-cloud systems, their architecture harbors an underexplored landscape of security vulnerabili…
arXiv:2611.00386v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on safeguards to prevent unauthorized actions while preserving legitimate service. However, existing risk assessments often focus on individual safeguard performance while overloo…
arXiv:2611.00447v1 Announce Type: new Abstract: LLM-as-a-judge scores are often distributionally shifted from human ratings on any given evaluation task, and post-hoc calibration (mapping LLM to human scores in a small labeled anchor set) has become a popular method to correct f…
arXiv:2611.00460v1 Announce Type: new Abstract: Large language models (LLMs) now answer medical exam questions at or above expert level, but it is unclear whether such scores reflect clinical competence, or are instead affected by the format of the questions being asked (e.g., m…
arXiv:2611.00504v1 Announce Type: new Abstract: LLMs are increasingly used to design heuristics for computer systems. However, most synthesis frameworks evaluate candidates by their average performance, which can mask severe regressions on specific workloads. Even adding adversa…
arXiv:2611.00544v1 Announce Type: new Abstract: Large language model (LLM) agents extend their capabilities with skills, each with a name, a description, and a body. Under progressive disclosure, an LLM router selects skills by name and description alone and loads only the selec…
arXiv:2611.00564v1 Announce Type: new Abstract: Web API recommenders return a set of APIs for a mashup request but do not check it against provider documentation, the main public evidence of an API's capabilities. The set can therefore contain unsupported or redundant APIs and m…
arXiv:2611.00971v1 Announce Type: new Abstract: Understanding the malware propagation dynamics over the Internet is crucial for effectively controlling its spread. Existing mechanistic and data-driven models in the context of malware propagation dynamics, have some issues with e…
arXiv:2611.01031v1 Announce Type: new Abstract: Reliable first-seen dates are important for constructing temporal malware evaluation splits, but this information often comes from external services that are not equally accessible to all researchers. We investigate whether machine…
arXiv:2611.01097v1 Announce Type: new Abstract: Decentralizing large language model (LLM) inference across untrusted Web nodes requires robust verification to ensure computational integrity. Existing activation-based verification and detection mechanisms validate intermediate ou…
arXiv:2611.01150v1 Announce Type: new Abstract: In recent years, the growing adoption of Edge AI systems has been accompanied by a surge in security threats. Edge AI deployments face an rapidly evolving spectrum of security threats, from side-channel information leakage to ad- v…
arXiv:2611.01585v1 Announce Type: new Abstract: Currently, long-chain LLM agents commonly suffer from behavioral degradation in complex tasks, where prompts are written in full but steps are not executed in full. To address this issue, existing approaches face three major challe…
arXiv:2611.03698v1 Announce Type: new Abstract: Recursive Self-Improvement (RSI) aims to enable AI systems to autonomously build and improve AI systems themselves, including models, harnesses, and underlying infrastructure. Within this broader agenda, a central capability is ena…
arXiv:2611.03723v1 Announce Type: new Abstract: Deep Research (DR) systems extend large language models into autonomous agents that decompose complex information needs, iteratively search the web, and synthesize evidence to answer challenging questions. However, their multi-stag…
arXiv:2611.03725v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) pipelines are widely used for domain-specific question answering, yet locating faults remains manual and time-consuming. Fault localization is challenging because RAG pipelines consist of interd…
arXiv:2611.04032v1 Announce Type: new Abstract: Serving an LLM efficiently depends on the engine, how the model is split across GPUs, precision, scheduler settings, speculative decoding, KV-cache management, and prefill-decode disaggregation. The best configuration depends on th…
arXiv:2611.03774v1 Announce Type: new Abstract: Most malware detection research focuses on identifying whether a file is malicious before it executes. Far less attention goes to what happens after infection. This paper presents an empirical analysis of post-infection malware beh…
arXiv:2611.04461v1 Announce Type: new Abstract: We evaluate, at implementation level and under an explicit threat model, the verification pipelines of three Verifiable Credential (VC) formats: SD-JWT VC; the W3C Verifiable Credentials Data Model 2.0 with the Data Integrity crypt…