activity
20112022
most citedEvasion Attacks against Machine Learning at Test Time

889 citations · 1.7k across the 11 of their papers we have counts for

collaborators

27 papers

cs.GT2022

Stateful Detection of Adversarial Reprogramming

Yang Zheng, Xiaoyi Feng, Zhaoqiang Xia +5

Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model tr…

cs.CR202110 cited

Fingerprint recognition with embedded presentation attacks detection: are we ready?

Marco Micheletto, Gian Luca Marcialis, Giulia Orrù +1

The diffusion of fingerprint verification systems for security applications makes it urgent to investigate the embedding of software-based presentation attack detection algorithms…

cs.LG2021

The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?

Antonio Emanuele Cinà, Sebastiano Vascon, Ambra Demontis +3

One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test ti…

cs.CV2020

Detecting Anomalies from Video-Sequences: a Novel Descriptor

Giulia Orrù, Davide Ghiani, Maura Pintor +2

We present a novel descriptor for crowd behavior analysis and anomaly detection. The goal is to measure by appropriate patterns the speed of formation and disintegration of groups…

cs.CV2020

Are spoofs from latent fingerprints a real threat for the best state-of-art liveness detectors?

Roberto Casula, Giulia Orrù, Daniele Angioni +3

We investigated the threat level of realistic attacks using latent fingerprints against sensors equipped with state-of-art liveness detectors and fingerprint verification systems w…

cs.LG2020259 cited

Adversarial Feature Selection against Evasion Attacks

Fei Zhang, Patrick P. K. Chan, Battista Biggio +2

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion and malware detection, although their security ag…