On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders
Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robust
今日共收录 1236 条安全情报,包含 262 个 CVE,575 篇安全通告,以及 100 篇研究论文。
← 返回归档列表Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robust
Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the pat
Perimeter triage faces a latency/semantics trade-off: signature engines are fast and format-safe but blind to unseen att
Facial recognition has become central to modern authentication systems, security frameworks, and personalized services.
Gate bootstrapping (GB) is a widely used technique in FHEW-like fully homomorphic encryption schemes, such as TFHE, for
Instruction-data selectors choose which instruction-following records are used for fine-tuning, improving alignment qual
Coding agents that run long enough must compact their context, summarizing the conversation, discarding the original, an
Finite-field inversion is a basic nonlinear building block in the design of S-boxes for symmetric cryptography. In inver
Message Queue Telemetry Transport (MQTT) is widely used in IoT environments due to its lightweight publish-subscribe des
Consider a standard multi-hop wireless radio network in which nodes relay messages for one another. While the contents o
Policy engines determine whether evaluated policies permit a request, but a correct ALLOW decision does not establish co
Malicious actors frequently obfuscate their code to hinder investigative reverse engineering efforts. Among the most for
Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, sour
A quantum computer could recover the key of any Ethereum account whose public key appears on chain. We prove that no sid
Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it.
Assembly language models (ALMs) are becoming important for automated binary analysis, yet their token-level interfaces o
Existing approaches to differential privacy in diffusion models rely on loose sensitivity bounds and isotropic Gaussian
Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies i
The weights of a trained network do not have uniform sensitivity to model accuracy: the 1% most sensitive weights carry
Adoption of artificial intelligence in K-12 schools has outpaced guidance for students, teachers, and administrators. Ex