CyberIntel ⬡ News
★ Saved ◆ Cyber Reads

// AI & Machine Learning
Intel Feed

cyberintel.kalymoon.com  ·  2926 articles  ·  updated every 4 hours · grows forever

2926Total
2881Full Text
May 21, 2026Latest
◈ Women in Cyber ◉ Threat Intelligence ◎ How-To & Tutorials ⬡ Vulnerabilities & CVEs 🔍 Digital Forensics ◍ Incident Response & DFIR ◆ Security Tools & Reviews ◇ Industry News & Leadership ✉ Email Security 🛡 Active Threats ⚠ Critical CVEs ◐ Insider Threat & DLP ◌ Quantum Computing ◬ AI & Machine Learning
🔥 Trending Topics · Last 48h
◬ AI & Machine Learning
Operationalising Cyber Risk Management Using AI: Connecting Cyber Incidents to MITRE ATT&CK Techniques, Security Controls, and Metrics

arXiv:2603.12455v1 Announce Type: new Abstract: The escalating frequency of cyber-attacks poses significant challenges for organisations, particularly small enterprises constrained by limited in-house…

arXiv Security Read →
◬ AI & Machine Learning
Hunting CUDA Bugs at Scale with cuFuzz

arXiv:2603.12485v1 Announce Type: new Abstract: GPUs play an increasingly important role in modern software. However, the heterogeneous host-device execution model and expanding software stacks make G…

arXiv Security Read →
◬ AI & Machine Learning
Keys on Doormats: Exposed API Credentials on the Web

arXiv:2603.12498v1 Announce Type: new Abstract: Application programming interfaces (APIs) have become a central part of the modern IT environment, allowing developers to enrich the functionality of ap…

arXiv Security Read →
◬ AI & Machine Learning
AEGIS: No Tool Call Left Unchecked -- A Pre-Execution Firewall and Audit Layer for AI Agents

arXiv:2603.12621v1 Announce Type: new Abstract: AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in…

arXiv Security Read →
◬ AI & Machine Learning
ExpanderGraph-128: A Novel Graph-Theoretic Block Cipher with Formal Security Analysis and Hardware Implementation

arXiv:2603.12637v1 Announce Type: new Abstract: Lightweight block cipher design has largely focused on incremental optimization of established paradigms such as substitution--permutation networks, Fei…

arXiv Security Read →
◬ AI & Machine Learning
Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw

arXiv:2603.12644v1 Announce Type: new Abstract: The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Framewor…

arXiv Security Read →
◬ AI & Machine Learning
Why Neural Structural Obfuscation Can't Kill White-Box Watermarks for Good!

arXiv:2603.12679v1 Announce Type: new Abstract: Neural Structural Obfuscation (NSO) (USENIX Security'23) is a family of ``zero cost'' structure-editing transforms (\texttt{nso\_zero}, \texttt{nso\_cli…

arXiv Security Read →
◬ AI & Machine Learning
Colluding LoRA: A Composite Attack on LLM Safety Alignment

arXiv:2603.12681v1 Announce Type: new Abstract: We introduce Colluding LoRA (CoLoRA), an attack in which each adapter appears benign and plausibly functional in isolation, yet their linear composition…

arXiv Security Read →
◬ AI & Machine Learning
FoSAM: Forward Secret Messaging in Ad-Hoc Networks

arXiv:2603.12871v1 Announce Type: new Abstract: Apps such as Firechat and Bridgefy have been used during recent protests in Hong Kong and Iran, as they allow communication over ad-hoc wireless network…

arXiv Security Read →
◬ AI & Machine Learning
Almost-Free Queue Jumping for Prior Inputs in Private Neural Inference

arXiv:2603.12946v1 Announce Type: new Abstract: Privacy-Preserving Machine Learning as a Service (PP-MLaaS) enables secure neural network inference by integrating cryptographic primitives such as homo…

arXiv Security Read →
◬ AI & Machine Learning
A Requirement-Based Framework for Engineering Adaptive Authentication

arXiv:2603.12968v1 Announce Type: new Abstract: Authentication is crucial to confirm that an individual or entity trying to perform an action is actually who or what they claim to be. In dynamic envir…

arXiv Security Read →
◬ AI & Machine Learning
Mitigating Collusion in Proofs of Liabilities

arXiv:2603.12990v1 Announce Type: new Abstract: Cryptocurrency exchanges use proofs of liabilities (PoLs) to prove to their customers their liabilities committed on-chain, thereby enhancing their trus…

arXiv Security Read →
◬ AI & Machine Learning
FraudFox: Adaptable Fraud Detection in the Real World

arXiv:2603.13014v1 Announce Type: new Abstract: The proposed method (FraudFox) provides solutions to adversarial attacks in a resource constrained environment. We focus on questions like the following…

arXiv Security Read →
◬ AI & Machine Learning
Purify Once, Edit Freely: Breaking Image Protections under Model Mismatch

arXiv:2603.13028v1 Announce Type: new Abstract: Diffusion models enable high-fidelity image editing but can also be misused for unauthorized style imitation and harmful content generation. To mitigate…

arXiv Security Read →
◬ AI & Machine Learning
Defensible Design for OpenClaw: Securing Autonomous Tool-Invoking Agents

arXiv:2603.13151v1 Announce Type: new Abstract: OpenClaw-like agents offer substantial productivity benefits, yet they are insecure by default because they combine untrusted inputs, autonomous action,…

arXiv Security Read →
◬ AI & Machine Learning
Verification of Robust Properties for Access Control Policies

arXiv:2603.13181v1 Announce Type: new Abstract: Existing methods for verifying access control policies require the policy to be complete and fully determined before verification can proceed, but in pr…

arXiv Security Read →
◬ AI & Machine Learning
Prompt Injection as Role Confusion

arXiv:2603.12277v1 Announce Type: cross Abstract: Language models remain vulnerable to prompt injection attacks despite extensive safety training. We trace this failure to role confusion: models infer…

arXiv Security Read →
◬ AI & Machine Learning
SpectralGuard: Detecting Memory Collapse Attacks in State Space Models

arXiv:2603.12414v1 Announce Type: cross Abstract: State Space Models (SSMs) such as Mamba achieve linear-time sequence processing through input-dependent recurrence, but this mechanism introduces a cr…

arXiv Security Read →
◬ AI & Machine Learning
DiscoRD: An Experimental Methodology for Quickly Discovering the Reliable Read Disturbance Threshold of Real DRAM Chips

arXiv:2603.12435v1 Announce Type: cross Abstract: State-of-the-art DRAM read disturbance mitigations rely on the read disturbance threshold (RDT) (e.g., the number of aggressor row activations needed …

arXiv Security Read →
◬ AI & Machine Learning
RTD-Guard: A Black-Box Textual Adversarial Detection Framework via Replacement Token Detection

arXiv:2603.12582v1 Announce Type: cross Abstract: Textual adversarial attacks pose a serious security threat to Natural Language Processing (NLP) systems by introducing imperceptible perturbations tha…

arXiv Security Read →
◬ AI & Machine Learning
ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents

arXiv:2603.12614v1 Announce Type: cross Abstract: Tool-augmented LLM agents increasingly rely on multi-step, multi-tool workflows to complete real tasks. This design expands the attack surface, becaus…

arXiv Security Read →
◬ AI & Machine Learning
SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking

arXiv:2603.12749v1 Announce Type: cross Abstract: Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns ca…

arXiv Security Read →
◬ AI & Machine Learning
Balancing the privacy-utility trade-off: How to draw reliable conclusions from private data

arXiv:2603.12753v1 Announce Type: cross Abstract: Absolute anonymization, conceived as an irreversible transformation that prevents re-identification and sensitive value disclosure, has proven to be a…

arXiv Security Read →
◬ AI & Machine Learning
Editing Away the Evidence: Diffusion-Based Image Manipulation and the Failure Modes of Robust Watermarking

arXiv:2603.12949v1 Announce Type: cross Abstract: Robust invisible watermarks are widely used to support copyright protection, content provenance, and accountability by embedding hidden signals design…

arXiv Security Read →
← Prev 114 / 122 Next →