AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
We have 3 of 60 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Heads of Security (HoS), a prompt injection defense that enforces instruction-data separation via a small set of learned per-head attention gates, is introduced and shows that prompt injection robustness can be achieved and improved through targeted attention interventions.
Models are usually aligned based on their observed outputs, using demonstrations, preference data, or reward signals. These objectives reward responses that look aligned. More capable models may learn to satisfy them without internalizing the intended behavior, for example by faking compliance during training. Such sup...
An architectural vulnerability is identified that circumvents anti-distillation mechanisms, allowing adversaries to extract a proprietary model's reasoning, as well as proposing concrete cryptographic and system-level mitigations to secure client-side reasoning.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.