RePAIR: Inverting Backdoor Attacks in Semantic Segmentation
Despite significant advances in computer vision, semantic segmentation models remain vulnerable to backdoor attacks, pos
2026-10-29 归档
今日共收录 3209 条安全情报，包含 2330 个 CVE，388 篇安全通告，以及 93 篇研究论文。
← 返回归档列表Too many clients spoil the logs: distributed parsing, aggregation techniques and metrics
Log messages are employed to identify anomalies in IoT systems and have been widely used across many applications. To en
Developing a Dynamic Multi-factor Authentication System for Securing Smart Organizations
As smart organizations increasingly rely on technologies like AI, big data, and IoT, securing these systems is crucial.
The Content Leash: Mitigating Degenerate Solutions in Invertible Speaker Anonymization
Voice anonymization aims to protect a speaker's identity while preserving the linguistic content of speech, enabling voi
Beyond LWE: Post-Quantum Assumptions under a Counterfactual Break of the Dihedral Coset Problem
A refuted 2026 claim of an efficient quantum algorithm for the Dihedral Coset Problem (DCP) motivates this survey of the
Quantifying and Prioritizing Stealthy Source-Manipulation Threats Against Multi-Source Anomaly Detectors
Security pipelines often fuse several data sources and protect a downstream model with a cross-source anomaly detector.
Haste Makes Waste? Towards Safe Few-Step Text-to-Image Models
While few-step distilled text-to-image models have gained traction due to their fast generation times, the speed-up impl
Silent Blindness: Fault Vulnerability of Hardware Malware Detectors
Hardware malware detectors (HMDs) classify hardware performance-counter measurements to identify malicious execution. Fa
Peak-DNA: Recurrent Morphology in Global Narrative Propagation
Global narrative streams exhibit noisy, fragmented, and asynchronous amplification bursts, making direct waveform compar
A Simple Presentation of Robust Membership Inference Attacks
In a membership inference attack, an attacker is given the data of a particular individual, and tries to determine if th
No Tokenizer, Still a Gap: Cross-Lingual Fairness of Homoglyph and Invisible-Character Watermarking
Homoglyph and invisible-character watermarks are edit-based watermarks. Instead of changing how a model generates text,
Evaluating Federated Vision-Language and Vision-Only Models for Privacy-Aware Breast Cancer Imaging
Artificial intelligence (AI) shows promise for breast imaging, but limited labeled data, institutional data fragmentatio
PHP2Shell and the Future of AI-Discovered Vulnerability Disclosure: Evidence, Verification, and Human Authority
AI-assisted vulnerability discovery can produce technically plausible findings faster than maintainers can validate, coo
Privately Clipping Heavy-Tailed Data
Summing vectors is a basic task in differentially private data analysis. Standard private sum algorithms clip vectors to
They Will See Johnny's Message: A Measurement Study of Post-Quantum Cryptography Across Email Delivery Paths
Harvest-now, decrypt-later (HNDL) attacks make the transition to post-quantum cryptography (PQC) urgent for email. This
I-HITL: Inalienable Human-in-the-Loop
Human oversight is a pillar of AI safety. It is often exercised by a human in the loop (HITL) who approves critical acti
Information-Theoretic Secure Aggregation With Heterogeneous Client Quantization
In federated learning (FL), secure aggregation enables a server to compute the sum of local model updates of $N$ clients
A Category-Selective Encryption Framework for Privacy Protection of UAV Images
Imagery captured by unmanned aerial vehicle (UAV) systems increasingly raises privacy concerns, as UAV aerial surveillan
Cheap AI-Assisted Reverse Engineering and What It Will Do
Generative AI is putting the law of reverse engineering (RE) under severe strain. Existing IP and technology laws assume
The Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service ope