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 …
⏱ Độ trễ thật của tab này: trung bình 7.1 giờ sau khi CVE được công bố (n = 5328, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.
arXiv:2510.12200v2 Announce Type: replace Abstract: Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosy…
arXiv:2611.13696v1 Announce Type: new Abstract: Multi-agent systems provide a convenient framework for the massive deployment of agents based on Large Language Models (LLMs). It provides a sound framework where agents can interact with existing software to perform actions in an …
arXiv:2611.10453v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) rollouts interleave model reasoning with tool calls in persistent workspaces. Scaling these rollouts incurs substantial memory costs for concurrent environments, while slow tool calls delay entir…
arXiv:2611.10756v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed as shared multi-tenant services, relying on advanced optimizations like KV cache and prefix sharing to improve throughput and reduce latency. However, these optimizations intro…
arXiv:2611.10843v1 Announce Type: new Abstract: Agentic AI systems extend large language models with tools, memory, retrieval, browser or computer-use interfaces, code execution, external services, and multi-agent coordination. Although these capabilities enable agents to act be…
arXiv:2611.10947v1 Announce Type: new Abstract: Cloud infrastructure threat modeling lacks empirical validation of AI-discovered threats. We present a three-phase methodology of multi-agent threat discovery, automated exploit synthesis, and non-destructive live validation, and a…
arXiv:2610.24379v1 Announce Type: new Abstract: Recent work shows that attackers can implant dormant malicious behaviors that remain hidden at release but emerge after benign fine-tuning. As foundation models are used as agents, whether dormant poisoning extends to harmful agent…
arXiv:2610.24896v1 Announce Type: new Abstract: LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We co-train attacker and defender instead, and let execution decide every reward…
arXiv:2610.26906v1 Announce Type: new Abstract: Variable type recovery is a critical task in binary reverse engineering, enabling downstream applications such as vulnerability discovery, malware analysis, and security enforcement. While recent Transformer-based models have demon…
arXiv:2610.31831v1 Announce Type: new Abstract: How can an AI agent automatically discover security vulnerabilities in any software repository? Existing approaches use LLMs to generate software vulnerability exploits. However, it is challenging for an LLM to reliably verify its …
arXiv:2610.33411v1 Announce Type: new Abstract: An AI agent can prepare an accurate report and still request an action its user has not authorized. Cooperation across Web services therefore requires separate judgments about identity, evidentiary support, and permission. We defin…
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks. Millions of such instructional videos are uploaded online every day, yet LLM agents remain unable to exploit this ever-expandin…
arXiv:2611.00407v1 Announce Type: new Abstract: An agent's visible score can exceed its real progress because it gamed the score or because it simply made mistakes, so a useful reward-hacking monitor must tell the two apart. We built a sandboxed task in which an agent can game a…
arXiv:2611.00489v1 Announce Type: new Abstract: Agentic systems are AI-powered technologies capable of autonomous action within digital environments, such as sending emails or making reservations. They are deeply connected to external tools as well as users' data and resources, …
arXiv:2611.01976v1 Announce Type: new Abstract: Large language model based agents increasingly rely on external tools to invoke services and interact with web resources. These tools can evolve through software updates, yet agentic frameworks may continue trusting them without re…
arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such agents has mostly lured them away from a real target that stays reachable. We study a different arrangement: an LLM defe…
arXiv:2605.03158v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) systems must link exploit code, advisories, and fix commits to the vulnerabilities they concern, and they must do so for vulnerabilities disclosed after training. HackerSignal is a public corpus …
arXiv:2611.16588v1 Announce Type: new Abstract: Affected-version ranges in vulnerability databases decide which deployments scanners, patching pipelines, and incident responders treat as vulnerable, yet these ranges are often incomplete, so vulnerable releases are silently treat…
arXiv:2611.10723v1 Announce Type: new Abstract: Security fixes usually reach users as compiled updates, but deployment delays leave unpatched systems exposed. During this window, comparing patched and unpatched binaries can reveal how to exploit a vulnerability, turning a defens…
arXiv:2610.25118v1 Announce Type: new Abstract: Biometric authentication systems increasingly use privacy-preserving mechanisms to protect sensitive templates. However, the authentication interface itself may still leak information that enables reconstruction attacks. Prior atta…
arXiv:2610.29308v1 Announce Type: new Abstract: Dynamic scheduling requires dispatching online arrivals while anticipating future jobs, as poor decisions can compound downstream costs under nonlinear tardiness objectives. We show that a pretrained large language model (LLM) can …
arXiv:2610.33489v1 Announce Type: new Abstract: LLM-powered agents increasingly rely on third-party skills that combine natural-language instructions with executable code, creating supply-chain risks that may span both artifacts. Existing skill scanners often rely on rule matchi…
arXiv:2611.00725v1 Announce Type: new Abstract: Coding agents increasingly operate with web access and high privileges, creating a new attack surface where web fraud can directly target autonomous agents. Existing studies mainly focus on malicious links, prompt injection, and in…
arXiv:2611.06294v1 Announce Type: new Abstract: Large language model (LLM) coding assistants and agents construct a repository context before generating code. For security-sensitive code, this context decides whether the model sees the project's safeguards (e.g., authorization c…
arXiv:2502.04953v2 Announce Type: replace Abstract: Static analysis techniques are often insufficient to determine whether a reported security vulnerability is exploitable and actually poses a real security risk to a software application. Dynamic analysis addresses this limitati…
arXiv:2611.08170v1 Announce Type: new Abstract: Scammers have increasingly adopted AI-driven capabilities, evolving from automated message generation to fully agentic conversational systems that scale operations and maximize the exploitation of fraudulent resources before detect…
Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-to-end reconstruction of 3D assets and their scene layouts, but still struggle with fine-grained scene geometry and asset quality. Meanwhile, specialized 3D object…
Bài báo phát hiện một lỗ hổng mới gọi là data‑void exploit trong các LLM thực hiện web‑search. Khi nội dung đáng tin cậy thiếu hụt, kẻ xấu có thể đưa tin giả vào “kho dữ liệu trống” và LLM sẽ trích dẫn chúng trong câu trả lời, gây lan truyền thông tin sai lệch.
Nghiên cứu về kỹ thuật tấn công trích xuất dữ liệu mật từ máy tính cô lập (air-gapped) bằng cách phát tín hiệu vô tuyến từ thanh RAM. Đây là tài liệu nghiên cứu phần cứng và bảo mật phần cứng rất đáng chú ý.
arXiv:2606.00625v2 Announce Type: replace Abstract: Reproducing software vulnerabilities is fundamental to security researchers, open-source maintainers, and educators. Yet, vulnerabilities are often hard to reproduce, and even when they can be reproduced once, recreating a soft…
arXiv:2610.23534v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make them candidates for future autonomous malware, where connectiv…
arXiv:2610.28794v1 Announce Type: new Abstract: Software supply chain attacks continue to be on the rise, exploiting the trust that helps open source ecosystems thrive. Recent incidents like the Shai-Hulud worm and the Axios compromise demonstrate that a single malicious package…
arXiv:2610.32278v1 Announce Type: new Abstract: Advanced attackers in post-exploitation scenarios increasingly craft attack chains that combine benign operations, configuration errors, and vulnerability exploitation to achieve objectives like privilege escalation. While such cha…
arXiv:2611.18126v1 Announce Type: new Abstract: Windows Hello is the primary authentication mechanism on over one billion Windows 11 devices, supporting PINs as short as four digits. Such low-entropy PINs are viable only because the TPM's anti-hammering protection mitigates brut…
arXiv:2603.10099v2 Announce Type: replace-cross Abstract: The 2020 United States Census adopted differential privacy to protect individual confidentiality, adding calibrated noise to summary demographic measurements that are then reconciled into population tables. We developed B…
Nghiên cứu đánh giá năng lực và hạn chế của các mô hình ngôn ngữ lớn (LLM) khi đóng vai trò là trình tối ưu hóa số học (numerical optimizers) trong không gian có chiều cao. Paper cung cấp khung đánh giá phân tách chất lượng giải pháp và lỗi thực thi.
arXiv:2611.13942v1 Announce Type: new Abstract: Cyberattacks against power systems increasingly exploit industrial communication and control dependencies arising from distributed energy resources (DER), remote management, and market-based incentives. Progress on intrusion detect…
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones. Using neural data to train large models from scratch or fully fine-tune them after task-pretraining has proven difficult because neural …
Autoregressive decoding relies on the KV cache, whose memory footprint grows linearly with context length and caps batch size and throughput. Existing post-training methods exploit redundancy across tokens, layers, and feature dimensions, or lower numerical precision. We identify…