ATHENA: A Framework based on Diverse Weak Defenses for Building Adversarial Defense
There has been extensive research on developing defense techniques against adversarial attacks; however, they have been mainly designed for specific model families or application domains, therefore, they cannot be easily extended. Based on the design philosophy of ensemble of diverse weak defenses, we propose ATHENA---a flexible and extensible framework for building generic yet effective defenses against adversarial attacks. We have conducted a comprehensive empirical study to evaluate several realizations of ATHENA with four threat models including zero-knowledge, black-box, gray-box, and white-box. We also explain (i) why diversity matters, (ii) the generality of the defense framework, and (iii) the overhead costs incurred by ATHENA.
Code (3)
Tasks
Adversarial DefenseDenoisingDiversityPhilosophySimilar Papers 제목 키워드 기반
Athena: Synergizing Data Prefetching and Off-Chip Prediction via Online Reinforcement Learning
Prefetching and off-chip prediction are two techniques proposed to hide long memory access latencies in high-performance processors. In this work, we demonstrate that: (1) prefetching and off-chip prediction often provid…
Reinforcement LearningA method for ethical AI in Defence: A case study on developing trustworthy autonomous systems
What does it mean to be responsible and responsive when developing and deploying trusted autonomous systems in Defence? In this short reflective article, we describe a case study of building a trusted autonomous system -…
EthicsTranslationA Transformer-based Response Evaluator for Open-Domain Spoken Conversation
Many open-domain dialogue systems rely on multiple response generators, any of which can contribute a response to the dialogue in a particular context. Thus the ability to compare potential responses and then select the …
Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot
Athena 2.0 is an Alexa Prize SocialBot that has been a finalist in the last two Alexa Prize Grand Challenges. One reason for Athena's success is its novel dialogue management strategy, which allows it to dynamically cons…
Dialogue ManagementManagementATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To address this limitation, we introduce ATHENA, …