AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
JITterFlip is presented, the first BFA targeting the host-side JIT serving control plane of GPU-based LLM inference, and develops a decision-guided fault-vulnerable code analysis that enables both gibberish output generation and a correct-output sponge attack.
This work presents Aray, a deterministic-first YARA interpreter and positive-fixture synthesizer, a deterministic-first YARA interpreter and positive-fixture synthesizer that validates generated fixtures against their source rules.
It is found that every one of five epilogue faults -- scale precision, double rounding, multiplication order, output truncation, fused ordering -- moves the output by at most a single bfloat16 spacing, and by exactly one whenever it moves it at all, across 5,880 cells.
This work presents the first systematic characterization of SDC vulnerability across major computation interfaces in both the forward and backward passes of Transformer training, and proposes TrainSDC, a characterization-guided protection framework consisting of Q/K-path recomputation, residual-gain monitoring, and exp...
This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. L...
A second, semantic draft source is proposed: the same pool, re-keyed by the hidden state the verifier has already computed at each committed token, together with a merge that lets it ride inside an existing lexical drafter's tree.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.