2 citations · 2 across the 6 of their papers we have counts for
6 papers
Cross-Session Threats in AI Agents: Benchmark, Evaluation, and Algorithms
Ari Azarafrooz
AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detect…
Language Alignment via Nash-learning and Adaptive feedback
Ari Azarafrooz, Farshid Faal
Recent research has shown the potential of Nash Learning via Human Feedback for large language model alignment by incorporating the notion of a preference model in a minimax game s…
Differentiable Neural Computers with Memory Demon
Ari Azarafrooz
A Differentiable Neural Computer (DNC) is a neural network with an external memory which allows for iterative content modification via read, write and delete operations. We show th…
Follow the Neurally-Perturbed Leader for Adversarial Training
Ari Azarafrooz
Game-theoretic models of learning are a powerful set of models that optimize multi-objective architectures. Among these models are zero-sum architectures that have inspired adversa…
Hierarchical Soft Actor-Critic: Adversarial Exploration via Mutual Information Optimization
Ari Azarafrooz, John Brock
We describe a novel extension of soft actor-critics for hierarchical Deep Q-Networks (HDQN) architectures using mutual information metric. The proposed extension provides a suitabl…
Fuzzy Hashing as Perturbation-Consistent Adversarial Kernel Embedding
Ari Azarafrooz, John Brock
Measuring the similarity of two files is an important task in malware analysis, with fuzzy hash functions being a popular approach. Traditional fuzzy hash functions are data agnost…