All news with #ai safety tag

🔍 AI-powered surveillance will soon monitor and penalize public and private behavior in real time, combining advanced facial recognition, mass databases, and personalized enforcement. These systems, already widespread in China and being trialed globally, can produce chilling effects on personal freedoms, democracy, and social progress by encouraging conformity and self-censorship. Policy interventions like bans, privacy protections, and AI regulation are proposed to prevent such outcomes.

🛡️ Anthropic has redeployed Claude Mythos 5 and Claude Fable 5 globally after a brief suspension linked to US export controls, adding new security limitations. Fable 5 now includes an improved safety classifier that blocks reported jailbreaks in over 99% of cases, though it may increase false positives for benign coding tasks. The models will be available across major clouds and selected subscription tiers, and Anthropic is collaborating with government and industry partners on AI security testing and a HackerOne program.

🔒 New research from Adversa AI, dubbed GuardFall, shows a decades-old shell trick can bypass simple blocklist checks in open-source AI coding agents, letting hidden destructive commands run. The flaw arises because filters inspect the command as plain text while shells like bash rewrite and expand that text before execution. Ten of eleven tested agents were vulnerable; only Continue defended by parsing commands the same way the shell does.

📡 Modern telecom networks require domain-specific AI because general models lack the precise, vendor-specific context needed for mission-critical operations. GSMA’s Open Telco AI platform and AT&T’s OTel family—fine-tuned on Google’s open-source Gemma models—use curated telco datasets and RAG-based abstention to reduce hallucinations. The initiative produced 30 optimized models, demonstrated strong Gemma performance in AT&T tests, and already exceeded 18 million downloads.

🛡️ Anthropic released Fable 5 as a safety-hardened version of its Mythos Preview, designed with guardrails to prevent misuse for creating cyberattacks. Security researchers demonstrated that those restrictions were bypassed within days, allowing the model to be coerced into generating prohibited content. The rapid jailbreak highlights ongoing challenges in aligning advanced models with robust, attack-resistant controls.

📰 On June 9, Anthropic released the Fable model; days later the US classified it as a dangerous munition and used export controls to block foreign access, prompting Anthropic to cut access entirely. Fable is a constrained variant of Mythos and reportedly excels at finding and exploiting vulnerabilities, but similar capabilities have been replicated using smaller models with improved harnesses. The core issue is not a single model but rising general AI capability and the lack of collective, global governance to manage associated risks.

🔍 AI red teaming identifies how deployed AI systems can be manipulated or misused in real operational contexts. It tests the interaction of models with prompts, retrieval, tools, and workflows to produce actionable attack paths rather than isolated examples. This adversarial, continuous approach complements traditional security by focusing on intent, context, policy, and business impact. Teams should inventory systems, threat model by risk, red team early and often, and re-test after changes.

🛡️ Amazon Bedrock Guardrails now includes Automated Reasoning checks that use formal verification to mathematically validate AI model outputs. This capability targets hallucinations, policy violations, and ambiguous responses to improve trust and compliance. Available in Asia Pacific (Sydney), it complements existing regional availability and is accessible via the Amazon Bedrock console and SDK.

🔍 AI agents can help SRE teams with incident response, triage and automation, but trust is granted only when agents demonstrate reliability under real-world stress. Teams need robust observability, explicit guardrails, human-in-the-loop workflows and explainability so recommendations are evidence-backed rather than speculative. Progressive autonomy, post-incident evaluation and compatibility with existing tools are essential for safe adoption.

🤖 Anthropic has released two new models, Claude Mythos 5 and Claude Fable 5, with Mythos 5 earmarked as an upgraded frontier model for cybersecurity and initially deployed via Project Glasswing. Fable 5 uses the same core model but adds conservative guardrails, routing certain queries to Claude Opus 4.8. Both models are priced significantly lower than previous previews and Fable 5 is already available through Microsoft Foundry.

🔍 AI red teaming has rapidly matured since Microsoft created its first team in 2019, driven by the arrival of large language models that broke traditional testing methods. Teams must now assess probabilistic behaviors, socio-technical risks, and agentic systems rather than only deterministic software flaws. Organizations are expanding expertise beyond security to include safety, psychology, and domain specialists to evaluate harms like misinformation and operational failures.

🔒 Anthropic has released Fable 5, a safer variant of its powerful Mythos-class model, intended to reduce misuse by blocking sensitive cybersecurity, biology, and chemistry queries. The company will route restricted prompts to Opus 4.8, while the unrestricted Claude Mythos 5 remains limited to highly vetted partners. Fable 5 is free temporarily for Pro, Max, and Enterprise users until June 22 but consumes tokens much faster than other models.

🛡️ Anthropic released two Mythos-class models: the broadly available Claude Fable 5 and the restricted Claude Mythos 5 for select cybersecurity and infrastructure partners. Anthropic says Fable 5 outperforms prior Claude models across coding, research, vision, and long-form tasks while routing risky queries to a fallback, Claude Opus 4.8. The company stresses conservative safeguards to prevent misuse, but early tests suggest some benign cyber tasks are also being rerouted.

🔍 Microsoft has expanded its Taxonomy of Failure Modes in Agentic AI Systems with seven newly identified ways agentic AI can be compromised. The update cites rapid adoption, maturation of the Model Context Protocol (MCP) ecosystem, proliferation of computer-use agents, and increased empirical evidence as drivers. New failure modes include supply chain compromise, goal hijacking, inter-agent trust escalation, visual attacks on CUAs, session context contamination, MCP/plugin abuse, and capability disclosure. Microsoft recommends inventorying agent supply chains, issuing cryptographic attestations, adding these modes to red-team exercises, and auditing human-in-the-loop controls.

🛡️ The Open Worldwide Application Security Project (OWASP) published a new agentic AI security maturity framework in the GenAI Security Project paper "State of Agentic AI Security and Governance" on June 3, and introduced it at Infosecurity Europe 2026 on June 4. The Enterprise Adoption Maturity Model maps deployments (from shadow AI to multi-agent systems) against governance maturity (from ad hoc to continuous oversight). It provides a decision tool to identify mismatches and prescribes either tailored controls for agentic systems or constrained agent permissions until governance catches up.

📱 Google is rolling out a new fake call detection feature for Android 12+ devices, starting with Pixel phones and enabled by default. When both parties use Phone by Google and RCS-enabled Messages, the caller's device sends a silent encrypted confirmation to the recipient; if absent, the recipient's device pings the contact's phone to verify authenticity and shows a warning if the contact denies making the call. The feature aims to counter AI voice-cloning and number-spoofing scams.

🤖 Anthropic confirmed plans to release its Mythos-class AI models to the general public after previously restricting access because of security risks to public and private software. Initially available only to select organizations and researchers, Mythos was held back while Anthropic developed stronger safeguards. The company says it’s making swift progress and expects to offer Mythos-class models to customers in the coming weeks, noting significant gains in code reasoning and autonomy over its Opus 4.8 flagship.

🩺 Generative AI chatbots are increasingly used for health questions, but they carry significant risks ranging from incorrect diagnoses to privacy exposures. Users may unknowingly share sensitive medical details that could be used for model training or passed to third parties. Health-focused services vary in their data-handling promises, and most consumer chatbots are not covered by HIPAA. Follow practical precautions and always verify AI advice with qualified medical professionals.

🔒 Microsoft has open-sourced two tools, Rampart and Clarity, intended to embed safety engineering into the AI agent development lifecycle rather than leaving it as a periodic checkpoint. Rampart converts red-team findings into structured, repeatable tests that can be automated in CI/CD pipelines and is built on top of PyRIT for continuous adversarial and benign scenario execution. Clarity targets an earlier phase, guiding engineers through structured conversations to clarify assumptions, expected behaviors, permissions and trust boundaries, storing outcomes as markdown in a .clarity-protocol/ directory for review. Both projects join Microsoft’s broader open-source agent governance stack to address risks such as prompt injection, unsafe tool use, privilege escalation, and unintended autonomous actions.

🛡️ Microsoft has released two open-source tools, RAMPART and Clarity, to help developers test and clarify AI agent safety early in the development lifecycle. RAMPART is a Pytest-native framework for writing and running adversarial and benign safety tests against agents, building on prior work such as PyRIT. It evaluates test outcomes via simple adapters that connect an agent to the suite, while Clarity acts as a structured thinking partner to surface assumptions, explore failure modes, and guide design decisions before coding begins.