PeopleofSuperintelligence

Researcher

Giuseppe Ateniese

Giuseppe Ateniese is a computer security researcher whose work spans secure data storage, machine-learning privacy and encrypted AI. He earned degrees at Salerno and Genoa, then coauthored work on provable data possession, classifier training-set leaks and GAN attacks on collaborative learning and passwords. At Stevens, he led computer science, co-developed Accenture’s editable blockchain prototype, and coauthored attacks on private training data and passwords; he also co-founded Keyless. He has been a professor and Eminent Scholar at George Mason since 2021, where he studies privacy-preserving machine learning and works on language-model fingerprinting and encrypted inference.

Badges

Timeline

  1. 1995–2000

    Computer science degrees

    He earns a Laurea in computer science at the University of Salerno in 1995, with Alfredo De Santis as his master’s advisor. He completes a computer science PhD at the University of Genoa in 2000 under Gene Tsudik.

  2. 2007

    Provable data possession

    In 2007, he coauthors “Provable Data Possession at Untrusted Stores,” the full version of an ACM CCS 2007 paper. Its protocol lets a client verify that an untrusted server possesses the original data through probabilistic proofs built from sampled blocks, without retrieving the data.

  3. 2013

    Hacking machine classifiers

    In 2013, he coauthors “Hacking Smart Machines with Smarter Ones” with Giovanni Felici, Luigi V. Mancini, Angelo Spognardi, Antonio Villani and Domenico Vitali. Their meta-classifier extracts meaningful information about other classifiers’ training sets.

  4. 2016–2021

    Chair at Stevens

    In 2016, he becomes director of Stevens’ Department of Computer Science and occupies the Farber Endowed Chair, established by Dave Farber and his late wife, Gloria. Stevens awards him an honorary Master of Engineering in 2020.

  5. September 2016

    Editable blockchain prototype

    In September 2016, Accenture unveils an editable blockchain prototype for permissioned systems, based on a modified chameleon hash function developed with him. Accenture and Ateniese register U.S. and E.U. patents for the invention.

  6. 2017

    GAN attacks and PassGAN

    In 2017, he coauthors “Deep Models Under the GAN” with Briland Hitaj and Fernando Perez-Cruz; its attack trains a GAN to generate prototypical samples from other participants’ private training data. He also coauthors PassGAN with Hitaj, Paolo Gasti and Perez-Cruz; it learns from leaked passwords and, with HashCat, matches 51%–73% more passwords than HashCat alone. He leads the Stevens study behind PassGAN.

  7. October 2019

    Co-founding Keyless

    By October 2019, he is a co-founder and Head of Research at Keyless, which aims to combine privacy-preserving cryptography and biometric authentication for online identity management.

  8. As of October 2026

    Professor and CCI Faculty Fellow

    In 2021, he joins George Mason University as Eminent Scholar in Cybersecurity, aiming to build a safe and private AI framework; he is a professor and CCI Faculty Fellow in Computer Science and Cyber Security Engineering. Earlier roles include teaching at Sapienza, assistant and associate professorships at Johns Hopkins, helping found its Information Security Institute, research at IBM Zurich and USC’s Information Sciences Institute, and a visiting professorship at Microsoft. His work covers privacy-preserving machine learning and blockchain-based decentralized secure computing; in 2025, he coauthors LLMmap to fingerprint language-model versions, and in 2026, he coauthors HEAT, a method for faster fully homomorphic inference.

Career

  1. Since 2021George Mason UniversityProfessor and Eminent Scholar in Cybersecurity; CCI Faculty Fellow in Computer Science and Cyber Security Engineering
  2. From 2019KeylessCo-founder and Head of Research
  3. 2016–2021Stevens Institute of TechnologyDirector; faculty chair
  4. Johns Hopkins UniversityFounder, Assistant Professor
  5. IBM ResearchResearcher
  6. University of Southern CaliforniaResearcher
  7. MicrosoftVisiting Professor

Education

  1. 2000University of GenoaPhD in computer science
  2. 1995University of SalernoLaurea in computer science

From the biography.

  1. 11% of AI doctorate holders from 2010 to 2016 founded or led a company or lab by 10 years after graduationIncludes Giuseppe Ateniese. We estimate how often AI doctorate holders founded or led a company or lab by 10 years after graduation, how waiting times compare between founders and top jobs, and which universities trained the most.
  2. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes George Mason University. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.
  3. The company share of AI researchers’ top papers was 31% in 2020–2024 and 8% in 1970–1974Includes George Mason University. We estimate where the people shaping AI worked when their most-cited papers appeared: the company share was 31% in 2020–2024 and 8% in 1970–1974, and Google led all organizations in 2020–2024.
  4. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes George Mason University. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.

Colleagues

People with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Giuseppe Ateniese yet. Send us a free-licensed photo.

  1. Giuseppe Ateniese ateniese.github.io. Checked 22 October 2026.
  2. Giuseppe Ateniese | College of Engineering and Computing cec.gmu.edu. Checked 22 October 2026.
  3. Provable Data Possession at Untrusted Stores ia.cr. Checked 22 October 2026.
  4. [1306.4447] Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers arxiv.org. Checked 22 October 2026.
  5. NewsPoints June 2016 web.stevens.edu. Checked 22 October 2026.
  6. Mason welcomes new Eminent Scholar in Cybersecurity | George Mason University gmu.edu. Checked 22 October 2026.
  7. Accenture Debuts Prototype of ‘Editable’ Blockchain for Enterprise and Permissioned Systems newsroom.accenture.com. Checked 22 October 2026.
  8. [1702.07464] Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning arxiv.org. Checked 22 October 2026.
  9. [1709.00440] PassGAN: A Deep Learning Approach for Password Guessing arxiv.org. Checked 22 October 2026.
  10. These Powerful New Password Crackers Challenge Our Notions of 'Secure' | Stevens Institute of Technology stevens.edu. Checked 22 October 2026.
  11. Biometric security startup Keyless raises $2.2M for encrypted data solution biometricupdate.com. Checked 22 October 2026.
  12. Faculty | Department of Computer Science cs.gmu.edu. Checked 22 October 2026.
  13. LLMmap: Fingerprinting for Large Language Models | USENIX usenix.org. Checked 22 October 2026.
  14. [2609.01730] HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation arxiv.org. Checked 22 October 2026.