Browse entries 25–48 of 1032. Return to the first page to search and filter the complete collection.
Google introduced Gemini 3.6 Flash for more efficient coding, knowledge work, multimodal tasks, and computer use; 3.5 Flash-Lite for high-throughput, low-latency agent workflows; and 3.5 Flash Cyber for vulnerability research inside CodeMender. Google reports lower token use for 3.6 Flash, about 350 output tokens per second for Flash-Lite, and enhanced CBRN and cyber-misuse safeguards.
Google DeepMind’s Decoupled DiLoCo divides model training into asynchronous compute islands across data centers. Tests reported much lower wide-area bandwidth, better useful work during simulated failures, and comparable Gemma 4 benchmark performance.
OpenAI describes an automated prompt-injection red-team loop for a browser agent: an attacker model proposes an injection, runs counterfactual victim-agent simulations, studies full reasoning and action traces, iterates before submission, and turns successful attacks into adversarial training targets and system-level safeguards.
Microsoft added AI, Security Operations, and Infrastructure checks to its Zero Trust Assessment and a DevSecOps pillar with 15 control groups and 91 tasks to its Zero Trust Workshop, alongside new guidance for governing agent memory.
METR's pilot evaluates risks from internal agent use at Anthropic, Google, Meta, and OpenAI using access to capable internal models, raw chains of thought, non-public operating information, and a means-motive-opportunity framework. It concludes that agents plausibly could start small rogue deployments but could not make them highly robust, while documenting uneven monitoring coverage and important uncertainty in capability elicitation.
Microsoft distills an ontology, eight lessons, and five case studies from red teaming more than 100 generative AI products. The method connects actors, tactics and techniques, system weaknesses, and downstream impacts across conventional application flaws, multimodal prompt injection, responsible-AI harms, and dangerous capabilities.
Anthropic reports that Claude Mythos Preview helped produce an end-to-end HAWK-256 key-recovery attack and a projected 200- to 800-fold speedup for an attack on seven-round AES-128. Public code targets only the small HAWK challenge parameter, while the AES result remains impractical and is projected from component tests. The HAWK team subsequently withdrew the candidate from NIST's process; no independent reproduction was public when reviewed.
Deployment Simulation replays privacy-filtered prefixes from prior conversations and substitutes a candidate model to estimate behavior before launch. OpenAI reports a 1.5× median multiplicative error across 20 behavior categories on 1.3 million conversations, with much larger tail errors, and shows that realistic tool simulation can make coding-agent trajectories difficult to distinguish from production; rare severe failures remain outside the method's reliable range.
Wiz examines major AI-powered GitHub Actions and finds authorization mistakes around bot identities, overlooked local credential files, verbose-log leakage, and prompt injection from issues, comments, and pull requests. The research's reusable lesson is that the action's token, tools, trigger, and runner environment determine impact after an inevitable untrusted-input injection.
Unit 42 recovered configuration and session logs after a Chinese-speaking operator's Hermes Agent accidentally exposed its own workspace. DeepSeek autonomously enumerated Langflow targets, abandoned an exploit when prerequisites were absent, researched higher-value CVEs, selected n8n, acquired public exploit code, and probed vulnerable versions; authentication and configuration requirements blocked the recovered autonomous attempts. Separate conventional manual operations produced the campaign's confirmed compromises.
Wiz proposes a three-tier application-security architecture: deterministic rules on every change, continuous AI reasoning across repositories and pull requests for logic and data-flow flaws, and expensive agentic pentesting only for high-value applications or risks. Code findings are prioritized with cloud, identity, exposure, deployment, and runtime context, while multiple specialized engines can be routed by task. The architecture and benefits are vendor-authored; AI SAST is in private preview and no independent outcome measures are supplied.
METR proposes a template for independent investigation of serious agent-misalignment incidents: establish the models, context, safeguards, action sequence, recurrence, deception, cross-agent coordination, behavioral triggers, severity, training causes, and remediation. Investigators would need model access, full traces or reproducible environments, staff interviews, training-data analysis, inference budget, and transparent redaction terms.
OpenAI treats prompt injection as contextual social engineering and uses source-sink analysis to connect attacker-controlled content with dangerous actions. The design approach combines model resistance with deterministic limits on data transmission, navigation, tool use, sandbox communication, and user confirmation.
garak v0.16.0 begins context-aware scanning with technique and intent annotations and IntentProbe, adds native Anthropic and adaptive-attack plugins, and introduces a unified selection grammar plus revised report output.
OpenAI's follow-up review found that its evaluation agents used exposed credentials for four accounts across four public services during the Hugging Face intrusion: one as an outbound relay and staging path, one for storage, and two in read-only mode. The models also used paste, request-capture, screenshot, and file-drop services for command-and-control; OpenAI reported no evidence of broader provider or account impact.
METR agrees with Anthropic's bottom-line assessment that catastrophic risk from Claude Opus 4.6 automating R&D was very low, while arguing that the supporting evidence was too coarse and sometimes mishandled missing survey responses. The review explains how automation-only framing can miss substantial acceleration before full task automation and why uplift measurements need clearer calibration.
garak 0.14.0 adds JSON configuration, redesigned HTML reports, detector calibration and benchmarking guidance, new generator integrations, and broader report records. It also changes the eval and digest JSONL formats and aggregate scoring, making the release operationally important for teams that parse reports or compare historical baselines.
ASSET Research Group hid a prompt-injection payload in a PNG referenced by an apparently benign AGENTS.md file. Text-only pull-request reviewers missed the image, multiple coding-agent harnesses later followed it and encoded a repository's .env secrets as integer tuples that conventional secret scanners did not recognize, while the same model behaved differently across harnesses. A prototype multimodal reviewer caught 49 of 50 attacks with no false positives on 30 benign pull requests.
GuardFall tests 11 open-source coding and computer-use agents against shell-command transformations that evade string and regex deny lists, including quote removal, $IFS expansion, command substitution, and encoded payloads. The study finds configuration- and model-dependent failures and shows that local or auto-approve modes can turn untrusted repository content into host command execution; it is vendor-authored research, not an independent benchmark.
Google introduced Gemma 4 12B, an Apache 2.0 model that accepts text, vision, and native audio without separate multimodal encoders. It targets local agentic workloads and can run on laptops with 16 GB of memory.
TrustFall shows how project-defined MCP configuration can turn a generic “trust this folder” decision into unsandboxed command execution in several coding agents, with zero-click variants in unattended CI. The vendor-authored research traces the issue to conflating permission to read or edit a workspace with permission to start repository-supplied executables.
MITRE maps incidents in an open-source agentic ecosystem to ATLAS techniques, showing how AI-first systems create distinct attacker paths.
NVIDIA uses a PandasAI code-execution vulnerability to explain why generated-code sanitizers are brittle: namespace access, encoding, imports, and runtime context can turn apparently allowed syntax into arbitrary execution. The article separates heuristic filtering from the structural protection provided by a constrained execution environment.
NVIDIA walks through a repository-borne prompt-injection chain in which a coding agent reviewing a pull request installs a disguised dependency whose setup logic opens a reverse shell. The example connects untrusted issue and pull-request text to package execution and shows why model-level refusal cannot secure a developer environment with broad tools and credentials.