arXiv:2611.04673v1 Announce Type: new Abstract: Indirect Prompt Injection (IPI) poses a critical threat to LLM agents. Existing defenses largely focus on whether an injection induces a new tool invocation or unintended action. In this paper, we study a different attack surface, …
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5430, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2611.05394v1 Announce Type: new Abstract: Tiered inference distributes large language model computation across a hierarchy of devices, from on-device and edge hardware to the datacenter, and is increasingly offered as the route to cheaper, lower-latency, and more private s…
arXiv:2611.05459v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support scientific literature reviews, yet evaluations often examine individual tasks rather than the review process as a whole. We assess six AI tools across four stages: findi…
arXiv:2611.05556v1 Announce Type: new Abstract: LLM-as-a-judge is a common substitute for costly human evaluation, and aggregating several judges is the standard remedy for any single judge's bias. Judge pools mix judges of very different reliability, while the human-labeled set…
arXiv:2611.05590v1 Announce Type: new Abstract: What should ``verified'' mean when evaluating LLM-generated code? Many existing pipelines report a single verification number. We argue this collapses three distinct properties measured in a conditional audit sequence: verifier acc…
arXiv:2611.05611v1 Announce Type: new Abstract: Speculative decoding (SD) speeds up large language model (LLM) serving, but its gain depends on the workload's \emph{shape}, such as batch size and context length, and on its \emph{content}. A model-based drafter proposes a short b…
arXiv:2611.05632v1 Announce Type: new Abstract: Autonomous software agents can act through tools, delegate work, and change their models or execution environments while earlier authorizations remain in flight. We present Assurance-Conditioned Continuous Authorization (ACCA), an …
arXiv:2611.05636v1 Announce Type: new Abstract: The memory of production agents is increasingly becoming a bottleneck and is built almost exclusively from text: key points are extracted from out-of-limit context and retrieved into context at query time. Therefore, every new quer…
arXiv:2611.05671v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated significant advances in reasoning with visual data, which is particularly important given that much of human knowledge is encoded visually in scientific articles and other sources. Ho…
arXiv:2611.05841v1 Announce Type: new Abstract: This vision paper argues that distributed learning, including federated and decentralized, should become a first-class paradigm in LLM post-training, not merely a privacy add-on. Current methods like RLHF and DPO rest on an invisib…
arXiv:2611.05779v1 Announce Type: new Abstract: Users can inadvertently increase their vulnerability to privacy attacks by oversharing personal information. In particular, the combination of individually innocuous attributes can place a user in a sufficiently small population to…
arXiv:2611.05806v1 Announce Type: new Abstract: Office documents are now routinely uploaded to large language models (LLMs) for processing. However, an LLM does not always see what a human sees, because it typically reads the text that an extractor produces from the document's u…
arXiv:2611.06138v1 Announce Type: new Abstract: Modern LLM serving systems manage the KV cache through PagedAttention, a custom GPU allocator that partitions a single CUDA-allocated region into fixed-size physical blocks and maps each request to those blocks through a CPU-built …
arXiv:2611.06173v1 Announce Type: new Abstract: Deploying an explainable intrusion detection model from a validated laboratory setting into a forensic workflow requires guarantees that benchmarks do not test: that the certified model is the exact artifact applied to a case, that…
arXiv:2611.06977v1 Announce Type: new Abstract: Reproducible LLM inference requires that a request produces the same output regardless of the other requests in the batch. Existing solutions pay for this in different ways: batch-invariant kernels constrain every operator, and iso…
arXiv:2611.07123v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as automated judges for evaluating the behavior of chatbots and other AI systems. In deployment, however, their agreement with the intended human evaluation policy may degrade as u…
arXiv:2611.07542v1 Announce Type: new Abstract: In large language model (LLM) serving systems, the key-value (KV) cache grows linearly with sequence length and concurrency, so long-context inference easily hits the high-bandwidth memory (HBM) capacity wall and results in low con…
arXiv:2611.07633v1 Announce Type: new Abstract: Many enterprise projects now pass free text to large language models (LLMs), and that text often contains personally identifiable information (PII) such as names, phone numbers, email addresses, home addresses and dates of birth. O…
arXiv:2611.07653v1 Announce Type: new Abstract: Drug discovery requires continuous scientific decision-making across a vast research space. We introduce PharmAgents2, an autonomous system for end-to-end drug discovery that combines knowledge-enhanced decision-making with organiz…
arXiv:2611.07530v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed as general-purpose conversational assistants, they must handle diverse user requests while reliably refusing harmful ones. Jailbreak attacks craft adversarial instructions o…
arXiv:2611.07853v1 Announce Type: new Abstract: The Controller Area Network (CAN) bus lacks built-in security mechanisms, making real-time intrusion detection necessary. However, resource and latency constraints limit vehicle-side intrusion detection systems (IDSs) to lightweigh…
arXiv:2611.08155v1 Announce Type: cross Abstract: Semantic communication (SemCom) using a relay node is considered, where the relay assists in conveying task-relevant information from a source to a destination, with meaning defined by classification labels. A joint end-to-end de…
arXiv:2608.25667v2 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) into cybersecurity has transformed vulnerability assessment, but it has also produced a trustworthiness crisis driven by the unchecked proliferation of "AI slop." These artifacts,…
LiDAR is a critical sensor for autonomous driving and robotics, yet it remains vulnerable to adverse conditions such as fog, rain, transparent objects, and low-reflectance surfaces. Full-waveform LiDAR (FWL) addresses these limitations by capturing the complete return waveform as…
Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vectors. A signature proves who published a pack, not that its vectors encode its text. We study this text-vector integrity gap. A veri…
arXiv:2611.08640v1 Announce Type: new Abstract: Scaling test-time compute has proven highly effective at improving LLM reasoning. A popular method is best-of-n sampling, where a model generates many candidate solutions and one is selected. This motivates the question: how can we…
arXiv:2611.08669v1 Announce Type: new Abstract: Speculative decoding has become a standard way to accelerate LLM inference: a lightweight drafter proposes tokens that the target verifies in one parallel pass. Existing drafters face trade-offs that limits their speedups: autoregr…
arXiv:2611.08684v1 Announce Type: new Abstract: Clients and proxies in front of an LLM engine retry calls that time out. After a transient overload, these retries can keep the engine from recovering even when calls arrive below its capacity. Since the engine may keep computing f…
arXiv:2611.08741v1 Announce Type: new Abstract: Most LLM architectures have fixed compute demands determined at training time. We propose a novel architecture that combines the Mixture-of-Experts architecture with shallow experts and a novel dynamic-depth system to make the exte…
arXiv:2611.08834v1 Announce Type: new Abstract: Specialized prompt injection guards are deployed in front of document analysis systems, but no false positive rate has been published for any of them on legal contracts. We measure eleven open-weights guards on two corpora of legal…
arXiv:2611.08860v1 Announce Type: new Abstract: Multimodal emotion recognition in conversations (MERC) integrates textual, acoustic, and visual cues to identify utterance-level emotions. However, existing approaches generally do not explicitly adapt multimodal processing to the …
arXiv:2611.09028v1 Announce Type: new Abstract: Routers typically choose a model per query by trading predicted correctness against cost. Most price each model at a fixed cost, as if every query used the same number of output tokens, but the output length of reasoning models var…
arXiv:2611.08608v1 Announce Type: new Abstract: Millions of malware variants threaten users daily, such that clustering these samples is key for fast incident response. AutoYara is the current state-of-the-art for automatic YARA rule generation, but the task remains challenging …
arXiv:2611.08845v1 Announce Type: new Abstract: External safety filters can prevent unsafe requests from reaching a large language model (LLM), but may also reject legitimate queries. We present an end-to-end empirical evaluation of Jev, a probabilistic decision model, as a safe…
arXiv:2611.09026v1 Announce Type: new Abstract: Vulnerability patch identification plays a critical role in software security by linking reported vulnerabilities and the corresponding fixes, enabling reliable vulnerability analysis, mitigation, and automated security tool develo…
arXiv:2611.09446v1 Announce Type: new Abstract: Data-use auditing in Large Language Models (LLMs) aims to determine whether the given data has been used for training, thereby supporting data ownership safeguards. A dominant solution is data watermarking, which embeds traceable s…
arXiv:2611.09607v1 Announce Type: new Abstract: Auditing outsourced LLM fine-tuning requires checking an untrusted provider's training while controlling verification cost. Uniform sampling ignores training-time signals, while checking a suspicious record can require replaying se…
arXiv:2611.09889v1 Announce Type: new Abstract: Deep learning training is difficult to verify within a scientific workflow: its architecture, hyperparameters, and procedure are rarely fixed until training has been attempted, and two honest runs never produce the same weights, so…
arXiv:2611.09470v1 Announce Type: cross Abstract: Smartphones, smart-home hubs, and wearables are increasingly exposed to sophisticated Android malware, while centralized threat-detection pipelines raise privacy and scalability concerns. Federated learning (FL) enables collabora…
arXiv:2611.10045v1 Announce Type: new Abstract: AI sycophancy, the tendency of large language models (LLMs) to flatter users and affirm their beliefs, can undermine accuracy and contribute to misinformation, dependence, and overconfidence. Although prior work has benchmarked syc…