Battista Biggio
PhD, Assistant Professor at PRA Lab, and Co-Founder of Pluribus One.
Twitter: @biggiobattista
New personal webpage (updated): battistabiggio.github.io
Press: May 25, 2021. Interview on Communications of ACM: Deceiving AI.
News: May 20, 2021. Lecture on "Trustworthy AI: Poisoning Attacks on AI" - AI for Good Trustworthy AI Seminar Series.
News: Invited speaker at CASA Distinguished Lecture Series on June 10, 2020. The video of my lecture "Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning" is available below.
News: Invited speaker at Avast's conference on CyberSec & AI, held in Prague, Czech Republic, on Oct. 25, 2019. The video of my lecture on Machine Learning Security: Adversarial Attacks and Defenses is available below.
Press: July 27, 2020. Short comment on Wired about AI/ML security testing in big companies and its automation in software development pipelines.
Press: May 11, 2020. Short comment on Wired about adversarial T-shirts against YOLO and R-CNN object detectors.
Press: Nov. 10, 2019. Short comment on NYT about Professor Dawn Song's work on adversarial stop signs.
Press: Aug. 30, 2019. Article on ZeroUnoWeb (in Italian) on AI security.
Press: Apr. 24, 2019. Interview on New Scientist about adversarial examples and AI.
Press: Mar 4, 2019. Interview on El Pais about deepfake videos (in Spanish).
Press: Feb 21, 2019, The Register features our recent article on transferability of adversarial attacks against machine learning here.
Press: Jan 03, 2019, Interview on Bloomberg about AI & hackers.
News: Invited speaker at the IBM workshop Nemesis '18, co-located with ECML-PKDD 2018 in Dublin. Slides available here.
News: Invited speaker at the "Winter School on Quantitative Systems Biology: Learning and AI", held in Trieste, Italy, on Nov. 15-16, 2018. The video of the first part of this lecture on Adversarial Machine Learning is available below (slides can be downloaded from the website of the school).
Press: April 29, 2018, Interview on WIRED "AI can help cybersecurity - if it can fight through the hype"
Press: March 9, 2018, Interview on WIRED "AI has a hallucination problem that's proving tough to fix"
Our ICCV 2017 Tutorial on Adversarial Pattern Recognition and Machine Learning is available on youtube. The associated review article "Wild Patterns: Ten Years after the Rise of Adversarial Machine Learning" is now on ArXiv: https://arxiv.org/abs/1712.03141. The tutorial webpage contains also slides from the follow-up editions at IJCAI-ECAI '18, EUSIPCO '18, ECCV '18, ACM CCS '18.
Short biography. Battista Biggio received the MSc degree in Electronic Engineering, with honors, and the PhD in Electronic Engineering and Computer Science, respectively in 2006 and 2010, from the University of Cagliari (Italy). Since 2007 he has been working for the Department of Electrical and Electronic Engineering of the same University, where he currently is an Assistant Professor. From May 12th, 2011 to November 12th, 2011, he visited the University of Tuebingen (Germany), and worked on the security of machine learning algorithms to contamination of training data.
Research interests. His research interests currently include:
- secure / robust machine learning and pattern recognition methods (adversarial learning);
- multiple classifier systems;
- and kernel methods;
with applications in biometric recognition, spam filtering, malware detection, and intrusion detection in computer networks.
- ICLR 2022, 2021
- CVPR 2020
- AAAI 2020, 2019
- IEEE Symp. on Security and Privacy 2022, 2021, 2020
- USENIX Sec. 2022, 2021, 2020
- IJCAI 2020, 2019, 2018
- NeurIPS 2021 (top reviewer), 2020, 2019
- ICML 2021, 2020, 2019
- ESANN 2019
- ICPR 2018 (Area Chair)
- NIPS 2018 workshops SECML, PPML, ACM CCS 2018, PANAMM 2018, AIST 2018, DLS 2018, co-located with IEEE Symp. S&P, ICPRAM 2018
- NIPS 2015, PRINF 2015, ICML 2014 Workshop on Learning, Security and Privacy, ACML 2013, AISec 2013, AISec 2014, AISec 2015, S+SSPR 2014, ICPR 2014.