cập nhật 15 phút trước

⏱ Độ trễ thật của tab này: trung bình 6.9 giờ sau khi CVE được công bố (n = 5187, sớm nhất 0.1 giờ). Số âm nghĩa là ta thấy trước ngày công bố.

20
Multi-User Multi-Key Image Steganography with Key Isolation
📄 Paper arXiv cs.CR 28 ngày trước

arXiv:2603.23005v2 Announce Type: replace Abstract: Steganography conceals secret information within innocuous carriers while preserving visual fidelity and enabling reliable recovery. Recent unified networks operate normally under untriggered conditions but switch to hidden ste…

🅲 hạng C
20
Neural Networks with Differentiable Belief-Function Layers
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30173v1 Announce Type: new Abstract: Yager's 1987 rule of combination $\boxplus$ was proposed on epistemic grounds: under high conflict, mass should be redistributed to ignorance rather than renormalised onto the class simplex. We observe that backpropagation needs th…

🅲 hạng C
20
When Stable and Preferred Semantics Agree: A Path-Based Approach
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30176v1 Announce Type: new Abstract: We investigate structural conditions under which preferred and stable semantics agree in abstract argumentation frameworks. Our approach is based on suitably chosen sets of paths in the attack graph and binary relations induced by …

🅲 hạng C
20
Breaking the high-degree barrier in Lehmer's problem with a human-AI discovery loop
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30277v1 Announce Type: new Abstract: While artificial intelligence has made rapid progress in mathematical reasoning, many open problems depend on structure that is revealed only through large-scale computational exploration and analytical synthesis. One such example …

🅲 hạng C
20
Can LLMs Improve Their Own Harness? A Controlled Study on ARC-AGI-3
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30499v1 Announce Type: new Abstract: A generally intelligent system acquires new skills efficiently without requiring humans to redesign its software scaffold for every new task. Yet language models rarely act alone. A harness is a symbolic program that orchestrates c…

🅲 hạng C
20
PLE: Physical-Engineering's Last Exam
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30537v1 Announce Type: new Abstract: Frontier language models now score above 90% on popular knowledge benchmarks and are increasingly deployed as agents that carry out multi-hour professional work. Yet no existing benchmark tests whether they can perform the real-wor…

🅲 hạng C
20
Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30582v1 Announce Type: new Abstract: AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the monitor. This avoids relying on a weaker reviewer the model coul…

🅲 hạng C
20
Anticipating Social Consequences with Distributional World Models
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30657v1 Announce Type: new Abstract: Social world models predict how interactions develop after an action, helping agents negotiate, cooperate and mediate. In these situations, one action can lead to several plausible futures, hence predicting only one future can over…

🅲 hạng C
20
Scaling Laws for Safety Probes
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30678v1 Announce Type: new Abstract: Safety probes trained on a model's activations are a standard tool for monitoring language models in real time. Each time a new model is released or a new harm area needs to be monitored, the probe must be retrained, which requires…

🅲 hạng C
20
Scaling Laws for Generative Reward Models
📄 Paper arXiv cs.AI 27 ngày trước

arXiv:2610.30765v1 Announce Type: new Abstract: We study generative reward models (GenRMs) as online preference providers for policy optimization in creative writing. Across Qwen3 reward-model sizes from 0.6B to 14B, Thinking judges trained with GRPO have higher static Gold-labe…

🅲 hạng C
20
Detecting AI Training in Datacentre Power
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30182v1 Announce Type: new Abstract: AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detect synchronous model training in facility-level power by Viter…

🅲 hạng C
20
When EVM Defaults Break: Three SDK Patterns for UTXO-Family Wallets
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30183v1 Announce Type: new Abstract: Mainstream Web3 SDKs (e.g., ethers.js, viem) bundle three coupled assumptions: an account-based ledger, a single secp256k1 signer, and input-selection-free transaction construction. These assumptions fail once a chain adopts an ext…

🅲 hạng C
20
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30202v1 Announce Type: new Abstract: With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Attackers can conceal malicious instructions within textual narr…

🅲 hạng C
20
The Psychology of an AI Hacker
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30361v1 Announce Type: new Abstract: Human hackers rely on composure, persistence, vigilance, and confidence under pressure. We investigate whether analogous emotion representations in AI models can improve cybersecurity AI performance. Using CT0, a 4B-parameter cyber…

🅲 hạng C
20
Rank Ceiling for Twiddle-Perturbation Faults on the Forward NTT
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30383v1 Announce Type: new Abstract: NIST standardised ML-KEM and ML-DSA in 2024 for post-quantum key establishment and digital signatures. Both compute forward number-theoretic transforms (NTTs) on secret polynomials. Published attacks zero every fixed multiplier, or…

🅲 hạng C
20
Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30439v1 Announce Type: new Abstract: Recent large reasoning models can infer where ordinary photos were taken using only visual information, creating a serious location privacy risk even when metadata and obvious geographic identifiers are removed. To understand the m…

🅲 hạng C
20
Membership Inference Attack on Private Evolution
📄 Paper arXiv cs.CR 27 ngày trước

arXiv:2610.30514v1 Announce Type: new Abstract: Synthetic Data Generation (SDG) is an actively studied way to enable safe sharing of private data more broadly. Inference-only SDG methods, such as Private Evolution (PE), are particularly appealing, as they can leverage black-box …

🅲 hạng C