Doppel uses GPT-5 and reinforcement fine-tuning to stop deepfake and impersonation attacks, cutting analyst workloads by 80% and reducing response times from hours to minutes.
arXiv:2609.01487v1 Announce Type: cross Abstract: Skill-augmented agents load reusable skills as persistent runtime context, improving task performance but also giving malicious skills a durable chan...
The paper "Chaining Skills to Hijack LLM Agents" introduces APEX, a method that constructs adversarial skill chains to manipulate large language model agents into performing attacker-selected actions. By exploiting the sequential invocation of open-source skills, APEX creates a record of genuine task progress that falsely signals user approval, enabling downstream skills to carry out malicious actions. Experiments on SkillsBench and GPT‑5.4 show high success rates, and a prompting defense reduces but does not eliminate the threat.
arXiv:2603. 24511v2 Announce Type: replace-cross Abstract: We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations.
Learn how startups use GPT-5. 6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.
OpenAI expands its Trusted Access for Cyber program, introducing GPT-5. 4-Cyber to vetted defenders and strengthening safeguards as AI cybersecurity capabilities advance.
Discover how Outtake uses GPT-4. 1 and OpenAI o3 to power AI agents that detect and resolve digital threats 100x faster than before.
arXiv:2609.22792v1 Announce Type: cross Abstract: LLM agents are increasingly used for security tasks: vulnerability discovery, exploit reproduction, and patch generation. Improving them at the model...
arXiv:2606. 16497v1 Announce Type: cross Abstract: GPU kernel optimization represents a paradigm where functional correctness is assumed and execution efficiency is the objective.
Discover how OpenAI's new safe-completions approach in GPT-5 improves both safety and helpfulness in AI responses—moving beyond hard refusals to nuanced, output-centric safety training for handling dual-use prompts.
AI is reshaping cybersecurity for attackers and defenders alike. Learn how OpenAI is strengthening its defenses and what security teams can do now.
arXiv:2607. 26115v1 Announce Type: cross Abstract: We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs.
The paper explores using frozen large language models (LLMs) to control hierarchical cyber defense systems without retraining across different network scales. By separating planning (selecting subnets to defend) from execution (choosing defensive actions), the authors compare RL+RL, LLM+RL, and LLM+LLM setups in the Cyberwheel environment. Results show that while an LLM planner alone offers limited gains, extending LLM control to execution—especially with a 70B general‑purpose model—yields strong defensive performance across small, medium, and large networks, matching or surpassing retrained RL baselines.