AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
This work introduces Gremlin, a system for generating adversarial benchmarks of queries with high headroom, and applies Bayesian optimization to search the joint space of queries and witness plans, seeking query-plan pairs that maximize headroom.
Large language model (LLM) agents are increasingly used for long-horizon research and engineering, yet evaluating these capabilities remains expensive, time-consuming, and heavily dependent on human expertise. This motivates a natural question: can LLM agents themselves construct efficient benchmarks that preserve the...
This work proposes VerTox, the first framework to formulate corpus poisoning as a verifiable reward-guided reinforcement learning (RLVR) problem, and produces adversarial documents that frequently rank higher than target documents across major neural ranking architectures, as well as a proprietary commercial embedding...
JevAdvBench is introduced, to the authors' knowledge the first adversarial benchmark for RLCD models, with 812 typed questions over 66 scenarios, and a black-box attack suite of 9,744 single-edit variants that each edit one part of a request, with billed input tokens confirming that the edit reached the model.
Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft adversarial examples, requiring neither access to model parameters nor architecture. Existing defenses predominantly rely on stochastic output perturbations, which fail to p...
It is proved that, under an honest-majority assumption and a representation-level separation condition, RAGSentinel exactly recovers a poison-free majority-sized context.
Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive mechanisms that can efficiently discover \textit{sets} of inputs that induce model failure. We introduce ATLAS (Adaptive Trust-Regions for Latent Adversarial Searches), wh...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.