Quadratic Extractors
arXiv:2611.07266v1 Announce Type: cross Abstract: A quadratic source is a random variable $X\sim\mathbb{F}_2^n$ generated by applying $n$ quadratics to a hidden…
EnglisharXiv cs.CR
最新资讯
言栖资讯收录 193592 篇 AI、开发与建站文章，按发布时间排序，支持搜索与按语言筛选。
FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning
arXiv:2611.08383v1 Announce Type: new Abstract: Federated learning servers combine client models with a fixed aggregation rule, and each rule in common use is d…
EnglisharXiv cs.CR
SensorGuard-RV: Sensor-to-Register Data Protection for Resource-Constrained RISC-V Devices
arXiv:2611.08380v1 Announce Type: new Abstract: Embedded systems rely on sensor measurements that traverse a complex hardware-firmware stack (e.g. peripheral in…
EnglisharXiv cs.CR
LABBA: LLM-Assisted Behavioral Biometric Authentication
arXiv:2611.08343v1 Announce Type: new Abstract: Behavioral biometrics have emerged as a promising complement to traditional physiological biometrics by leveragi…
EnglisharXiv cs.CR
Escalate or Close: How Fast-Tier Models Handle Held-Out Web Attack Families in Two-Tier Triage
arXiv:2611.08229v1 Announce Type: new Abstract: In two-tier triage a fast model decides most web requests and escalates the rest to a slow tier, so an attack th…
EnglisharXiv cs.CR
Zirah: A Post-Quantum True Random Number Generator Hardware Signer With an Avalanche Noise
arXiv:2611.08200v1 Announce Type: new Abstract: Zirah is a hardware signer built around an STM32F407 microcontroller, and its purpose is to find out, on inexpen…
EnglisharXiv cs.CR
The Promise of Strategic Agentic Scambaiting
arXiv:2611.08170v1 Announce Type: new Abstract: Scammers have increasingly adopted AI-driven capabilities, evolving from automated message generation to fully a…
EnglisharXiv cs.CR
Cloudy Skies: Early Detection of Jamming Against Iridium LEO Satellite-IoT Links
arXiv:2611.08118v1 Announce Type: new Abstract: Low Earth Orbit (LEO) satellite-IoT systems increasingly provide connectivity to mobile assets in remote areas, …
EnglisharXiv cs.CR
KeHoSu: Keyed Homoglyph Substitution for Authenticated Text Provenance over Copy-Paste Channels
arXiv:2611.08046v1 Announce Type: new Abstract: Nowadays, large language models produce text at scale, and much of it is redistributed across platforms. A moder…
EnglisharXiv cs.CR
CANMentor: A Large-Small Model Collaboration Framework for CAN Bus Intrusion Detection
arXiv:2611.07853v1 Announce Type: new Abstract: The Controller Area Network (CAN) bus lacks built-in security mechanisms, making real-time intrusion detection n…
EnglisharXiv cs.CR
Beyond Instruction Override: Benchmarking Indirect Prompt Injection with Task-Tampering Attacks
arXiv:2611.07640v1 Announce Type: new Abstract: Indirect prompt-injection (IPI) benchmarks predominantly test planted instructions that redirect a tool-using ag…
EnglisharXiv cs.CR
A Gingerbread House for LLM Agents: Source-Planned Honeypots That Lure Autonomous Attackers into an Isolated Shadow
arXiv:2611.07611v1 Announce Type: new Abstract: LLM agents can exploit web vulnerabilities fast enough that patching may come too late. Deception against such a…
EnglisharXiv cs.CR
JailBound: FOL-Guided Jailbreak Evaluation for Exploring LLM Behavioral Boundaries
arXiv:2611.07530v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly deployed as general-purpose conversational assistants, they mus…
EnglisharXiv cs.CR
AMORT-V1: Checkpointed Post-Quantum Attestation for Industrial Controllers
arXiv:2611.07476v1 Announce Type: new Abstract: Programmable logic controllers often remain deployed for decades, making post-quantum attestation a long-term re…
EnglisharXiv cs.CR
Breaking $\mathsf{TraintoDefend}$ via Adaptive Neuron Clustering in Cryptanalytic Model Extraction
arXiv:2611.07370v1 Announce Type: new Abstract: Cryptanalytic model extraction poses a fundamental threat to deep learning model confidentiality by enabling pre…
EnglisharXiv cs.CR
SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection
arXiv:2611.07222v1 Announce Type: new Abstract: Tool-using agents act on email, files, and payments, so an instruction hidden in a web page or a shared document…
EnglisharXiv cs.CR
Global Surveillance Under the Lens: Reconstructing Passive Dolev-Yao Intruders
arXiv:2611.07170v1 Announce Type: new Abstract: Global surveillance systems record large volumes of network traffic for retrospective analysis, but packet captu…
EnglisharXiv cs.CR
What an LLM API Actually Costs Per Month (Real Numbers, Not List Prices)
What an LLM API Actually Costs Per Month (Real Numbers, Not List Prices) I search "llm api cost per month" about once a quarter. Every time I get per-million-to…
Englishdev.to AI
I built a small macOS terminal that lets you take back a prompt you sent to Claude Code
lmux is a small macOS terminal I use to run a bunch of Claude Code and Codex sessions at once. The feature I reach for most is taking back a prompt I sent to th…
Englishdev.to AI
Final Round AI vs LockedIn AI vs Parakeet AI: what their refund policies actually say (Nov 2026)
Most people compare interview copilots on features. Latency, stealth, which models they use. Fair enough. But the complaints I keep reading on Trustpilot and G2…
Englishdev.to AI