Episode 4: Adversarial Attacks (on the efficiency) on AI Algorithms

🚨HIT the FOLLOW button and click on the BELL icon to get notified when I drop new episodes PODCAST DETAILS: ✅ Spotify: ⁠https://open.spotify.com/show/53meKeZGCMQdVKUoWfnu5x?si=pRxpMGYpSUKaqjAhauTP8w⁠  Apple Podcast: ⁠https://podcasts.apple.com/ca/podcast/ai-podcast/id1689350103⁠ 🆘 Please check out the other videos on the Podcast series: ⁠https://youtube.com/playlist?list=PLV9VnT1svgQTRrlf_GopP0JiSUIpzOtjr⁠ Efficiency-based Adversarial Attacks are a new area of research that looks into increasing the processing time of an AI system by multiple folds using adversarial attacks. This area of research is particularly important for safety-critical systems with real-time output. Welcome to my latest podcast with Mirazul Haque, a Ph.D. candidate at The University of Texas at Dallas. His lab specializes in the efficiency attack on AI systems. IMPORTANT LINKS: ✅ Mirazul's LinkedIn: https://www.linkedin.com/in/mirazul-haque-b4b331a6/ ✅ Here are some of the research papers from the lab: https://dl.acm.org/doi/pdf/10.1145/3510003.3510088 https://openaccess.thecvf.com/content_CVPR_2020/papers/Haque_ILFO_Adversarial_Attack_on_Adaptive_Neural_Networks_CVPR_2020_paper.pdf https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_NICGSlowDown_Evaluating_the_Efficiency_Robustness_of_Neural_Image_Caption_Generation_CVPR_2022_paper.pdf https://openreview.net/pdf?id=r88Isj2alz PODCAST DETAILS: ✅ Spotify: ⁠https://open.spotify.com/show/53meKeZGCMQdVKUoWfnu5x?si=pRxpMGYpSUKaqjAhauTP8w⁠ ✅ Apple Podcast: ⁠https://podcasts.apple.com/ca/podcast/ai-podcast/id1689350103⁠ ✅ YouTube Podcast: ⁠https://youtube.com/playlist?list=PLV9VnT1svgQTRrlf_GopP0JiSUIpzOtjr⁠ Follow me on: ✅ LinkedIn: ⁠https://www.linkedin.com/in/debangsha-sarkar/ ⁠ ✅ Twitter: ⁠https://twitter.com/DebangshaSarkar ⁠ ✅ Youtube: ⁠https://www.youtube.com/@artificialliai