Securing Agent-Generated Code with Its Own Development History
Pull requests written by coding agents can pass a project's test suite while omitting a guard or a validation step. To f
2026-10-27 归档
今日共收录 787 条安全情报，包含 0 个 CVE，405 篇安全通告，以及 97 篇研究论文。
← 返回归档列表Back to Basics: Formal Analysis Hints Improve Weak-to-Strong Monitoring
Frontier agentic systems are capable of taking misaligned actions that may cause significant harm. Monitoring techniques
Ranking Is Not Deciding: Benchmark Shortcuts and Operating-Point Collapse in Query-Time RAG Poisoning Defenses
Query-time filters that screen each retrieved document before it reaches the generator are the dominant published defens
A Rowhammer attack on Fil-C's software capabilities
Rowhammer is a hardware vulnerability in dynamic random-access memory (DRAM) in which repeated accesses to one or more a
Extraction meets Distillation - cryptanalytic techniques to recover parameters from a Deep Neural Network
We study fully connected neural-network reconstruction by combining cryptanalytic weight-direction extraction with learn
Security evaluation of 6G-oriented and O-RAN networks through targeted attacks
The sixth generation (6G) of networks is supported by increased bandwidth, automation through the use of O-RAN technolog
Pacifo: An Efficient Fully Homomorphic Encryption-based Lightweight ResNet for Trustworthy Machine Learning as a Service
Machine Learning as a Service (MLaaS) has become a popular paradigm for deploying AI applications. However, it raises si
Bounds on polynomial approximations of the discrete logarithm function
We revisit a classical result of Coppersmith and Shparlinski showing bounds on how well polynomials can approximate the
Combinatorial Lock for Trojan-Resilient AI Engines via Hash-Assisted Spectral Filtering
Multi-trigger backdoor attacks, in which heterogeneous trigger mechanisms (e.g., patch, blend, warping, and the latent-d
Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping
Cybersecurity operators increasingly encounter sophisticated and fast-paced attacks, making autonomous cyber defense (AC
Holo-NN: Holographic Nearest Neighbor Search via Compressive Sensing
In the age of AI, privacy-preserving approximate nearest neighbor (ANN) search over high-dimensional embeddings has emer
A-GE: Privacy-Preserving Age Assurance via Fine-Grained Motion
Age assurance faces a fundamental privacy dilemma: meaningful assurance typically requires revealing identity or other s
STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks
We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simpl
EVSEFuzz : A Tool for Automated Testing of Protocol Implementations
The rapid adoption and development of electric vehicle (EV) networks has required the expansive deployment of EV chargin
Quantum Cadence: Post-Quantum Consensus with Multiple Concurrent Proposers
The consensus protocols of most high-performance blockchains use quorum certificates, which bundle the signatures of a q
Developing Security Metrics for Automated Compliance Checking
To automatically check for compliance with security-related standards, prose requirements must be translated to technica
Identity Amortization: Shared Resources and the Cost of Sybil Attacks
Sybil defenses commonly price identities by requiring a resource for each one. When one resource can support several ide
Iterative Behavioral Identification for Covert Misappropriation Attacks
We present a data-driven, three-phase framework for covert misappropriation attacks on closed-loop networked control sys
Privacy-Preserving Federated Loss Exploration for Vision-Based Perception under Non-IID Data
Vision-based image classification models benefit from Federated Learning (FL) across vehicles, however learning accurate
Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation
AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in los