Giorgio Severi

25 papers A* 4A 1B 1C 1Journal 15Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	GRP-Obliteration: Unaligning LLMs With a Single Unlabeled Prompt. CoRR Mark Russinovich, Yanan Cai, Keegan Hines, Giorgio Severi, Blake Bullwinkel, Ahmed Salem
2026	J	`jnl`	The Trigger in the Haystack: Extracting and Reconstructing LLM Backdoor Triggers. CoRR Blake Bullwinkel, Giorgio Severi, Keegan Hines, Amanda J. Minnich, Ram Shankar Siva Kumar, Yonatan Zunger
2025	J	`jnl`	A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks. CoRR Blake Bullwinkel, Mark Russinovich, Ahmed Salem, Santiago Zanella-Béguelin, Daniel Jones, Giorgio Severi, Eugenia Kim, Keegan Hines, Amanda J. Minnich, Yonatan Zunger, Ram Shankar Siva Kumar
2025	J	`jnl`	A Systematization of Security Vulnerabilities in Computer Use Agents. CoRR Daniel Jones, Giorgio Severi, Martin Pouliot, Gary Lopez, Joris de Gruyter, Santiago Zanella-Béguelin, Justin Song, Blake Bullwinkel, Pamela Cortez, Amanda J. Minnich
2025	J	`jnl`	Lessons From Red Teaming 100 Generative AI Products. CoRR Blake Bullwinkel, Amanda J. Minnich, Shiven Chawla, Gary Lopez, Martin Pouliot, Whitney Maxwell, Joris de Gruyter, Katherine Pratt, Saphir Qi, Nina Chikanov, Roman Lutz, Raja Sekhar Rao Dheekonda, Bolor-Erdene Jagdagdorj, Eugenia Kim, Justin Song, Keegan Hines, Daniel Jones, Giorgio Severi, Richard Lundeen, Sam Vaughan, Victoria Westerhoff, Pete Bryan, Ram Shankar Siva Kumar, Yonatan Zunger, Chang Kawaguchi, Mark Russinovich
2025	—	`conf`	Model-agnostic clean-label backdoor mitigation in cybersecurity environments. MILCOM Giorgio Severi, Simona Boboila, John T. Holodnak, Kendra Kratkiewicz, Rauf Izmailov, Michael J. De Lucia, Alina Oprea
2024	A*	`conf`	Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning. ICLR Harsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan R. Ullman
2024	J	`jnl`	Model-agnostic clean-label backdoor mitigation in cybersecurity environments. CoRR Giorgio Severi, Simona Boboila, John T. Holodnak, Kendra Kratkiewicz, Rauf Izmailov, Alina Oprea
2024	J	`jnl`	Phantom: General Trigger Attacks on Retrieval Augmented Language Generation. CoRR Harsh Chaudhari, Giorgio Severi, John Abascal, Matthew Jagielski, Christopher A. Choquette-Choo, Milad Nasr, Cristina Nita-Rotaru, Alina Oprea
2024	A*	`conf`	Privacy Side Channels in Machine Learning Systems. USENIX Security Symposium Edoardo Debenedetti, Giorgio Severi, Milad Nasr, Christopher A. Choquette-Choo, Matthew Jagielski, Eric Wallace, Nicholas Carlini, Florian Tramèr
2023	—	`conf`	Ask and You Shall Receive (a Graph Drawing): Testing ChatGPT's Potential to Apply Graph Layout Algorithms. EuroVis (Short Papers) Sara Di Bartolomeo, Giorgio Severi, Victor Schetinger, Cody Dunne
2023	J	`jnl`	Ask and You Shall Receive (a Graph Drawing): Testing ChatGPT's Potential to Apply Graph Layout Algorithms. CoRR Sara Di Bartolomeo, Giorgio Severi, Victor Schetinger, Cody Dunne
2023	J	`jnl`	Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning. CoRR Harsh Chaudhari, Giorgio Severi, Alina Oprea, Jonathan R. Ullman
2023	A	`conf`	Poisoning Network Flow Classifiers. ACSAC Giorgio Severi, Simona Boboila, Alina Oprea, John T. Holodnak, Kendra Kratkiewicz, Jason Matterer
2023	J	`jnl`	Poisoning Network Flow Classifiers. CoRR Giorgio Severi, Simona Boboila, Alina Oprea, John T. Holodnak, Kendra Kratkiewicz, Jason Matterer
2023	J	`jnl`	Privacy Side Channels in Machine Learning Systems. CoRR Edoardo Debenedetti, Giorgio Severi, Nicholas Carlini, Christopher A. Choquette-Choo, Matthew Jagielski, Milad Nasr, Eric Wallace, Florian Tramèr
2022	C	`conf`	Bad Citrus: Reducing Adversarial Costs with Model Distances. ICMLA Giorgio Severi, Will Pearce, Alina Oprea
2022	J	`jnl`	Bad Citrus: Reducing Adversarial Costs with Model Distances. CoRR Giorgio Severi, Will Pearce, Alina Oprea
2022	—	`conf`	Network-Level Adversaries in Federated Learning. CNS Giorgio Severi, Matthew Jagielski, Gökberk Yar, Yuxuan Wang, Alina Oprea, Cristina Nita-Rotaru
2022	J	`jnl`	Network-Level Adversaries in Federated Learning. CoRR Giorgio Severi, Matthew Jagielski, Gökberk Yar, Yuxuan Wang, Alina Oprea, Cristina Nita-Rotaru
2021	A*	`conf`	Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers. USENIX Security Symposium Giorgio Severi, Jim Meyer, Scott E. Coull, Alina Oprea
2021	A*	`conf`	Subpopulation Data Poisoning Attacks. CCS Matthew Jagielski, Giorgio Severi, Niklas Pousette Harger, Alina Oprea
2020	J	`jnl`	Exploring Backdoor Poisoning Attacks Against Malware Classifiers. CoRR Giorgio Severi, Jim Meyer, Scott E. Coull, Alina Oprea
2020	J	`jnl`	Subpopulation Data Poisoning Attacks. CoRR Matthew Jagielski, Giorgio Severi, Niklas Pousette Harger, Alina Oprea
2018	B	`conf`	Malrec: Compact Full-Trace Malware Recording for Retrospective Deep Analysis. DIMVA Giorgio Severi, Tim Leek, Brendan Dolan-Gavitt