Shehory, Onn
Defending via strategic ML selection
Farchi, Eitan, Shehory, Onn, Barash, Guy
The results of a learning process depend on the input data. There are cases in which an adversary can strategically tamper with the input data to affect the outcome of the learning process. While some datasets are difficult to attack, many others are susceptible to manipulation. A resourceful attacker can tamper with large portions of the dataset and affect them. An attacker can additionally strategically focus on a preferred subset of the attributes in the dataset to maximize the effectiveness of the attack and minimize the resources allocated to data manipulation. In light of this vulnerability, we introduce a solution according to which the defender implements an array of learners, and their activation is performed strategically. The defender computes the (game theoretic) strategy space and accordingly applies a dominant strategy where possible, and a Nash-stable strategy otherwise. In this paper we provide the details of this approach. We analyze Nash equilibrium in such a strategic learning environment, and demonstrate our solution by specific examples.
Reports of the Workshops of the 32nd AAAI Conference on Artificial Intelligence
Bouchard, Bruno (Université du Québec à Chicoutimi) | Bouchard, Kevin (Université du Québec à Chicoutimi) | Brown, Noam (Carnegie Mellon University) | Chhaya, Niyati (Adobe Research, Bangalore) | Farchi, Eitan (IBM Research, Haifa) | Gaboury, Sebastien (Université du Québec à Chicoutimi) | Geib, Christopher (Smart Information Flow Technologies) | Gyrard, Amelie (Wright State University) | Jaidka, Kokil (University of Pennsylvania) | Keren, Sarah (Technion – Israel Institute of Technology) | Khardon, Roni (Tufts University) | Kordjamshidi, Parisa (Tulane University) | Martinez, David (MIT Lincoln Laboratory) | Mattei, Nicholas (IBM Research, TJ Watson) | Michalowski, Martin (University of Minnesota School of Nursing) | Mirsky, Reuth (Ben Gurion University) | Osborn, Joseph (Pomona College) | Sahin, Cem (MIT Lincoln Laboratory) | Shehory, Onn (Bar Ilan University) | Shaban-Nejad, Arash (University of Tennessee Health Science Center) | Sheth, Amit (Wright State University) | Shimshoni, Ilan (University of Haifa) | Shrobe, Howie (Massachusetts Institute of Technology) | Sinha, Arunesh (University of Southern California.) | Sinha, Atanu R. (Adobe Research, Bangalore) | Srivastava, Biplav (IBM Research, Yorktown Height) | Streilein, William (MIT Lincoln Laboratory) | Theocharous, Georgios (Adobe Research, San Jose) | Venable, K. Brent (Tulane University and IHMC) | Wagner, Neal (MIT Lincoln Laboratory) | Zamansky, Anna (University of Haifa)
The AAAI-18 workshop program included 15 workshops covering a wide range of topics in AI. Workshops were held Sunday and Monday, February 2–7, 2018, at the Hilton New Orleans Riverside in New Orleans, Louisiana, USA. This report contains summaries of the Affective Content Analysis workshop; the Artificial Intelligence Applied to Assistive Technologies and Smart Environments; the AI and Marketing Science workshop; the Artificial Intelligence for Cyber Security workshop; the AI for Imperfect-Information Games; the Declarative Learning Based Programming workshop; the Engineering Dependable and Secure Machine Learning Systems workshop; the Health Intelligence workshop; the Knowledge Extraction from Games workshop; the Plan, Activity, and Intent Recognition workshop; the Planning and Inference workshop; the Preference Handling workshop; the Reasoning and Learning for Human-Machine Dialogues workshop; and the the AI Enhanced Internet of Things Data Processing for Intelligent Applications workshop.