arXiv:2610.30450v1 Announce Type: new Abstract: Reasoning LLMs often continue reasoning after reaching a correct answer, wasting computation and sometimes replacing it with an incorrect one. Deciding when to stop is a metareasoning problem: the model must weigh what further reas…
⏱ Độ trễ thật của tab này: trung bình 6.8 giờ sau khi CVE được công bố (n = 5439, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2610.30696v1 Announce Type: new Abstract: When a multilingual LLM agrees with a user's false premise, is it being sycophantic, or does it simply not know better in that language? Current research does not distinguish these cases: they record only whether the model agreed, …
arXiv:2610.30193v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt injection. Yet RAG protection studies use in…
arXiv:2610.30516v1 Announce Type: new Abstract: In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as text transmitted to a decoder, who attempts to recover it. The success of this private-message transmission is co…
arXiv:2610.30626v1 Announce Type: new Abstract: The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting important for ownership protection and offline auditing. Existing fingerprinting methods typically construct evid…
arXiv:2610.30798v1 Announce Type: new Abstract: Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JIT) compilation frameworks such as Triton. Triton compiles GPU kernels through an MLIR/LLVM-based pipeline. We i…
arXiv:2610.31246v1 Announce Type: new Abstract: Multi-exit networks improve inference efficiency by allowing inputs to terminate early at intermediate exits. We identify a privacy vulnerability in cloud deployments of these networks: a malicious Cloud Service Provider (CSP) can …
arXiv:2610.30229v1 Announce Type: cross Abstract: Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the patients who contributed them. However, a model can reveal whether a patient's records were used in training, a …
arXiv:2610.30345v1 Announce Type: cross Abstract: Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robustness to adversarial perturbations at the receiver input remains underexplored. We show that standard gradient…
arXiv:2610.31937v1 Announce Type: new Abstract: Modern Large Language Models (LLMs) remain vulnerable to carefully orchestrated multi-turn interactions that progressively bypass safety mechanisms. However, many existing red-teaming approaches rely on heuristics or impose strong …
arXiv:2610.32181v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to support decisions under incomplete information, where deciding what to look up and when to stop matters as much as the final answer. However, LLMs fall into an information trap:…
arXiv:2610.32229v1 Announce Type: new Abstract: Training large language models (LLMs) in sub-8-bit arithmetic promises substantial gains in memory bandwidth and compute throughput, yet FP4 formats introduce quantization error severe enough to destabilize optimization if left una…
arXiv:2610.31695v1 Announce Type: new Abstract: Safety guards check content before an LLM application acts on it, and most paste that content into a plain-text prompt. Content that imitates the prompt can append a second task, and the guard answers that one instead. We call this…
arXiv:2610.31995v1 Announce Type: new Abstract: As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, approximate unlearning has emerged as a practical alternative to expensive full retr…
arXiv:2610.32017v1 Announce Type: new Abstract: LLM-generated code is increasingly reused across downstream applications and often undergoes identifier renaming or structural refactoring, making robustness to functionality-preserving edits essential for generative multi-bit code…
arXiv:2610.32626v1 Announce Type: new Abstract: Vision-based image classification models benefit from Federated Learning (FL) across vehicles, however learning accurate models from distributed vehicular cameras is challenging due to data heterogeneity and privacy concerns. To im…
arXiv:2610.32226v1 Announce Type: cross Abstract: No domestic legislature has ever reviewed a state's decision to authorise an autonomous cyber weapon before it acted. Closing the international attribution gap is necessary but not sufficient for democratic accountability. We for…
arXiv:2610.32238v1 Announce Type: cross Abstract: Governments govern AI-generated online harms from commercial platforms (EU DSA, AI Act, UK Online Safety Act), yet the most severe class remains ungoverned: autonomous cyber weapons (ACWs) deployed by nation-states against civili…
arXiv:2602.12630v3 Announce Type: replace Abstract: Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We critically ask how to achieve verifiabl…
arXiv:2610.33182v1 Announce Type: new Abstract: Large language model (LLM) agents are widely used in many applications and often rely on external tools. Tool information, such as function descriptions, helps agents determine which tools best suit a given context. However, attack…
arXiv:2610.33352v1 Announce Type: new Abstract: Large Language Models (LLMs) promise significant efficiency gains across information-intensive operations by automating repetitive language-based tasks. However, adoption decisions remain largely opportunistic, as organizations str…
arXiv:2610.33716v1 Announce Type: new Abstract: Automated vulnerability detection in binary executables is challenging due to the lack of source code and the limited semantic information available at the assembly level. Despite significant progress in machine-learning-based code…
arXiv:2610.33756v1 Announce Type: new Abstract: Automated vulnerability detection in C source code is a long-standing challenge, as traditional static analysis tools often trade precision for scalability and struggle with complex vulnerability patterns. Recently, large language …
arXiv:2610.33849v1 Announce Type: new Abstract: Query-time filters that screen each retrieved document before it reaches the generator are the dominant published defense against retrieval-augmented generation poisoning, and they report near-perfect detection on domain benchmarks…
arXiv:2610.33924v1 Announce Type: new Abstract: Mapping CVEs to MITRE ATT&CK techniques helps defenders translate vulnerability information into hypotheses about adversary behavior. Automating this mapping is challenging because relevant evidence is fragmented across heterogeneo…
arXiv:2610.34248v1 Announce Type: new Abstract: As a core component of modern RAG systems, approximate nearest neighbor (ANN) search has been extensively studied for decades. In practice, deploying ANN often requires symmetric privacy, where the querier's query and the database …
arXiv:2610.34290v1 Announce Type: new Abstract: Broken access control (BAC) ranks among the most severe web-application vulnerability classes, yet its automated repair remains largely unexplored. Unlike memory-safety vulnerabilities, BAC is a logic vulnerability whose repair dem…
Scientific discovery often begins with an unexpected observation that prompts a new research question. In a world with altered physical laws, can large language models (LLMs) notice unexpected behavior, such as heavier objects falling more slowly, and discover the law through exp…
arXiv:2610.33267v1 Announce Type: new Abstract: LLMs often answer semantically equivalent queries inconsistently, even when the underlying facts are known. We formalize consistency as semantic invariance over equivalence classes of queries and show that invariance under arbitrar…
arXiv:2610.33277v1 Announce Type: new Abstract: Engineering standards are challenging knowledge sources for large language models (LLMs) because they are hierarchical, multimodal, and densely connected through figures, tables, cross-references, and normative rules. Existing retr…
arXiv:2610.33391v1 Announce Type: new Abstract: The frontier of large language model (LLM) performance has advanced rapidly in recent years, fueled by scaling laws for pretraining on large text corpora. However, mainstream LLMs have fundamental limitations: they generate text au…
arXiv:2610.33448v1 Announce Type: new Abstract: The development of large language models (LLMs) are capable to assist with hardware experiments. In this scenario, this raises a practical question: Can LLMs determine whether a proposed operation is safe for a specific development…
arXiv:2610.33644v1 Announce Type: new Abstract: Research ideas are always proposed under resource constraints: a plan must fit the available compute, API credit, and time. Yet evaluations of research-ideation agents mostly score unconstrained novelty or overlap with a published …
arXiv:2610.36188v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on reusable skills for complex software engineering tasks, making skill libraries essential for repository development and maintenance. However, repository-specific skills must ev…
arXiv:2610.36415v1 Announce Type: new Abstract: Tool-assisted planning success can reflect external search and verification, leaving a model's unaided planning ability unresolved. We isolate innate planning through complete plans generated in one response without tools or execut…
arXiv:2610.36453v1 Announce Type: new Abstract: LLM agents that answer questions and act on behalf of users must decide when to yield to a user who disagrees. Disagreement may correct a genuine error or may be an attempt at manipulation. Prior work shows that models frequently a…
arXiv:2610.36258v1 Announce Type: new Abstract: Multi-turn jailbreaks turn dialogue safety into a trace property: a violation may become identifiable only when user intent and assistant behavior are considered across multiple turns. Existing guard models largely classify individ…
arXiv:2610.36334v1 Announce Type: new Abstract: AI-assisted vulnerability discovery can produce technically plausible findings faster than maintainers can validate, coordinate, and safely disclose them. The resulting challenge is not only to establish whether a vulnerability cla…
arXiv:2610.37061v1 Announce Type: new Abstract: All traditional encryption schemes share a fundamental operational vulnerability: encrypted data must be decrypted before it can be used. Fully homomorphic encryption eliminates this vulnerability by enabling computation directly o…
arXiv:2610.37488v1 Announce Type: new Abstract: Model quantization has become a fundamental technique for enabling the efficient deployment of large-scale deep neural networks (DNNs) in data-intensive applications by reducing model size. Despite its widespread adoption, the impa…