Recent coverage of #ai-security remains predominantly skeptical, with nearly half of articles in the past month taking a bearish stance. The 250 indexed articles reflect sustained concern about vulnerabilities and risks as artificial intelligence systems become more prevalent. Anthropic and its Claude model dominate discussions alongside emerging systems like GPT-5, while research from arXiv–CS AI forms the bulk of technical analysis. Sentiment has held relatively stable over the past 90 days, suggesting these security concerns represent ongoing rather than newly emerged challenges. Coverage frequently intersects with #cybersecurity, #machine-learning, #ai-safety, and #adversarial-attacks, indicating security issues span multiple technical domains. Browse the articles below to understand the specific threats and defensive approaches currently under scrutiny.
Researchers developed TT-SEAL, a selective encryption framework for compressed AI models using Tensor-Train Decomposition that maintains security while encrypting only 4.89-15.92% of parameters. The system achieves the same robustness as full encryption while reducing AES decryption overhead in end-to-end latency from 58% to as low as 2.76%.
Anthropic alleges that Chinese AI companies DeepSeek, Moonshot, and MiniMax conducted massive distillation attacks against its Claude AI system, creating 24,000 accounts and making 16 million exchanges to scrape training data. This represents a significant case of AI model theft and highlights growing tensions in the global AI competition.
Meta and other major AI companies have restricted the use of OpenClaw, a viral agentic AI tool, due to security concerns. The tool is recognized for its high capabilities but criticized for being wildly unpredictable in its behavior.
OpenAI has released a new crypto security tool following a costly incident where AI-generated code from Claude caused a $2.7 million bug that affected Moonwell users. The timing suggests a response to growing concerns about AI-generated code vulnerabilities in cryptocurrency applications.
OpenAI and Paradigm have launched EVMbench, a new benchmark tool designed to evaluate AI agents' capabilities in detecting, patching, and exploiting high-severity vulnerabilities in smart contracts. This collaboration represents a significant step toward improving smart contract security through AI-powered analysis tools.
SlowMist security firm has identified 472 malicious AI skills on the OpenClaw AI hub containing dangerous code. This represents a growing trend of hackers targeting AI plugins and extensions to gain access to cryptocurrency investors' devices.
Google DeepMind and the UK AI Security Institute (AISI) are strengthening their collaboration on critical AI safety and security research. This partnership aims to advance research in AI safety measures and security protocols.
OpenAI has released a system card for GPT-5.1-CodexMax detailing comprehensive safety measures including specialized training against harmful tasks and prompt injections. The document outlines both model-level and product-level mitigations such as agent sandboxing and configurable network access controls.
OpenAI is resisting the New York Times' request for access to 20 million private ChatGPT conversations, while simultaneously implementing enhanced security and privacy protections for user data. This legal dispute highlights growing tensions over data privacy and corporate access to AI conversation logs.
Prompt injections represent a significant security vulnerability in AI systems, requiring specialized research and countermeasures. OpenAI is actively developing safeguards and training methods to protect users from these frontier attacks.
OpenAI has launched Aardvark, an AI-powered autonomous security researcher that can find, validate, and help fix software vulnerabilities at scale. The system is currently in private beta with early testing available through sign-up.
OpenAI has announced progress on its partnership with the US CAISI and UK AISI to enhance AI safety and security systems. The collaboration focuses on strengthening safeguards and security measures for AI development and deployment.
CyberSecEval 2 is a comprehensive evaluation framework designed to assess cybersecurity risks and capabilities of Large Language Models. The framework aims to provide standardized metrics for evaluating AI model security vulnerabilities and defensive capabilities in cybersecurity contexts.
AI company terminated accounts linked to state-affiliated threat actors attempting to use AI models for malicious cybersecurity purposes. Investigation revealed that the AI models provided only limited incremental capabilities for such malicious activities.
OpenAI and other leading AI laboratories are strengthening AI governance through voluntary commitments focused on safety, security, and trustworthiness. This represents a proactive industry approach to self-regulation in AI development.
Researchers have developed adversarial images that can consistently fool neural network classifiers across multiple scales and viewing perspectives. This breakthrough challenges previous assumptions that self-driving cars would be secure from malicious attacks due to their multi-angle image capture capabilities.
An AI assistant developer conducted a security test inviting 2,000 people to attempt hacking their system, revealing vulnerabilities in AI safety and adversarial robustness. The exercise demonstrates both the challenges of securing AI systems against coordinated attacks and the importance of red-teaming in identifying real-world attack vectors before malicious actors exploit them.
Meta has hired the founders of Virtue AI to strengthen its artificial intelligence security capabilities. This strategic acquisition centralizes AI safety expertise within Meta and signals the company's commitment to addressing AI security concerns, potentially influencing industry standards and shifting competitive dynamics in the AI sector.
A systematic analysis of AI code generation security reveals that while models understand secure coding principles theoretically, they frequently fail to implement them correctly in practice. The research identifies substantial gaps between knowledge and execution, offering a framework to measure progress and suggesting principle-guided approaches as a path forward.
Researchers propose a decoupled evaluation framework for testing LLM-based penetration testing agents by separating reconnaissance from exploitation tasks. The study reveals significant capability gaps: agents achieve 90% success with accurate vulnerability context but only 50% autonomous reconnaissance performance, with distinct strengths across different architectural designs.
Researchers present a red teaming framework using multi-role LLM architecture to systematically expose vulnerabilities in large language models, particularly unfaithfulness in responses. The approach achieved up to 7.9% improvement in attack success rates, demonstrating that architectural design choices significantly impact model safety more than parameter scaling.
Researchers propose Intent-Governed Access Control (IGAC), a new authorization framework that restricts AI agent tool access based on user intent rather than static credentials alone. The system ensures that user requests can only narrow permissions, never expand them, addressing security risks where agents misuse authorized tools beyond their stated purpose.
Researchers introduce LAVA, a hierarchical framework using convolutional autoencoders to detect audio deepfakes and identify their source generation models with 95%+ accuracy. The system addresses a critical gap in deepfake attribution, moving beyond detection to pinpoint which specific AI model created fraudulent audio content.
Revelio is a new AI-powered framework that detects memory safety vulnerabilities in large codebases using large language models combined with executable proof-of-concept generation and deterministic sanitizer verification. The system discovered 19 previously unknown vulnerabilities in production projects while maintaining cost-efficiency, addressing the hallucination problem endemic to LLM-based security analysis.
Researchers have developed an autonomous synthetic media detection system that can identify deepfakes and attribute them to their source generators, while automatically adapting to new generative AI models without human intervention. The system uses open-set identification and unsupervised clustering to continuously learn and update its detection boundaries as the generative landscape evolves. This advancement addresses a critical gap in content authentication as AI-generated media becomes increasingly sophisticated.
