1 code implementation • 24 Feb 2017 • Briland Hitaj, Giuseppe Ateniese, Fernando Perez-Cruz
Unfortunately, we show that any privacy-preserving collaborative deep learning is susceptible to a powerful attack that we devise in this paper.
3 code implementations • 1 Sep 2017 • Briland Hitaj, Paolo Gasti, Giuseppe Ateniese, Fernando Perez-Cruz
State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes.
no code implementations • ICLR 2018 • Pablo M. Olmos, Briland Hitaj, Paolo Gasti, Giuseppe Ateniese, Fernando Perez-Cruz
In this paper, we noticed that even though GANs might not be able to generate samples from the underlying distribution (or we cannot tell at least), they are capturing some structure of the data in that high dimensional space.
1 code implementation • 5 Dec 2019 • Malhar Jere, Loris Rossi, Briland Hitaj, Gabriela Ciocarlie, Giacomo Boracchi, Farinaz Koushanfar
We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image.
no code implementations • 30 Oct 2020 • Dorjan Hitaj, Briland Hitaj, Sushil Jajodia, Luigi V. Mancini
To this date, CAPTCHAs have served as the first line of defense preventing unauthorized access by (malicious) bots to web-based services, while at the same time maintaining a trouble-free experience for human visitors.
no code implementations • 21 Jan 2022 • Dorjan Hitaj, Giulio Pagnotta, Briland Hitaj, Fernando Perez-Cruz, Luigi V. Mancini
Proposed as a solution to mitigate the privacy implications related to the adoption of deep learning, Federated Learning (FL) enables large numbers of participants to successfully train deep neural networks without having to reveal the actual private training data.
no code implementations • 12 Feb 2022 • Giulio Pagnotta, Dorjan Hitaj, Briland Hitaj, Fernando Perez-Cruz, Luigi V. Mancini
Being trained on proprietary information, these models provide a competitive edge for the owner company.
1 code implementation • 20 Apr 2022 • Loris Giulivi, Malhar Jere, Loris Rossi, Farinaz Koushanfar, Gabriela Ciocarlie, Briland Hitaj, Giacomo Boracchi
We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks.
no code implementations • 6 Oct 2022 • Huascar Sanchez, Briland Hitaj
We refer to this process of influence-seeking and trust-building as trust ascendancy.
no code implementations • 27 Feb 2023 • John Hester, Briland Hitaj, Grant Passmore, Sam Owre, Natarajan Shankar, Eric Yeh
Prior work has demonstrated that machine learning can be useful in determining efficient variable orderings.
no code implementations • 1 Mar 2023 • Eric Yeh, Briland Hitaj, Sam Owre, Maena Quemener, Natarajan Shankar
We evaluate CoProver on a series of well-established metrics originating from the recommender system and information retrieval communities, respectively.
no code implementations • 20 Mar 2023 • Eric Yeh, Briland Hitaj, Vidyasagar Sadhu, Anirban Roy, Takuma Nakabayashi, Yoshito Tsuji
Of interest for architects is to use these methods to generate design proposals from conceptual sketches, usually hand-drawn sketches that are quickly developed and can embody a design intent.
1 code implementation • 2 Jun 2023 • Javier Rando, Fernando Perez-Cruz, Briland Hitaj
Large language models (LLMs) successfully model natural language from vast amounts of text without the need for explicit supervision.
no code implementations • 6 Mar 2024 • Dorjan Hitaj, Giulio Pagnotta, Fabio De Gaspari, Sediola Ruko, Briland Hitaj, Luigi V. Mancini, Fernando Perez-Cruz
We introduce MaleficNet 2. 0, a novel technique to embed self-extracting, self-executing malware in neural networks.