Javier Carnerero Cano

Javier Carnerero Cano

PhD Researcher in Machine Learning Security

Imperial College London

About Me

(Last updated: April 2023)

Welcome! I am Javier, a PhD Candidate in AI Security in the Dept. of Computing at Imperial College London. My current interests are (not limited to) adversarial machine learning, aiming to investigate the security of machine learning algorithms; bilevel optimization problems; Generative Adversarial Networks (GANs); and federated learning. I focus on data poisoning attacks, where attackers can manipulate training data collected from untrusted sources to degrade the ML algorithm’s performance. I am part of the Resilient Information Systems Security (RISS) Group under the supervision of Prof Emil C. Lupu and Dr Luis Muñoz González.

For a high-level and fun presentation of my research interests in data poisoning, you can have a look at this video:


I have worked as a teaching assistant in several courses in ML, deep learning, and probabilistic methods at Imperial College London. I did a research internship in summer 2022 at IBM Research on ML security and machine unlearning.

I have extensive experience in prototyping ML algorithms in Python and PyTorch. My background is also in Telecom Engineering. In 2021 I was included in the Santander-CIDOB 35 under 35 List:


If you want to know fun facts about me, you can have a look at this video:


I am passionate about travelling. I am eager to learn, analytical, deliberative and achiever. I am always interested in challenges and open to new collaborations. Drop me an email or DM me on LinkedIn to connect!

Interests

  • Machine Learning
  • Deep Learning
  • Adversarial Machine Learning and Data Poisoning
  • Bilevel Optimization
  • Generative Adversarial Networks
  • Federated Learning

Education

  • PhD in Machine Learning Security, (exp.) 2023

    Imperial College London

  • MRes (Hons) in Multimedia and Communications, 2017

    Universidad Carlos III de Madrid

  • MSc (Hons) in Telecommunications Engineering, 2017

    Universidad Carlos III de Madrid

  • BEng (Hons) in Telecommunications Engineering, 2015

    Universidad Carlos III de Madrid

Experience

 
 
 
 
 

Research Intern, AI Security and Privacy

IBM Research

Jun 2022 – Aug 2022 Dublin, Ireland
Researched the security of machine unlearning methods.
 
 
 
 
 

Teaching Assistant, Dept. of Computing

Imperial College London

Oct 2019 – Dec 2022
Assisted in lab sessions and tutorials and marked coursework in the Dept. of Computing:

 
 
 
 
 

PhD Researcher, Machine Learning Security

Imperial College London

May 2018 – Present London, United Kingdom

Researching the security of machine learning in the Dept. of Computing: analyzing the vulnerabilities of machine learning algorithms, designing effective attacks and evaluating their impact, and proposing defenses that can help these algorithms to be more robust to adversaries. Special focus on data poisoning attacks. Techniques developed based on bilevel optimization and Generative Adversarial Networks.

Assisted in the supervision of 2 MSc (one of them passed with Distinction), 1 MEng, and 1 Undergraduate Research Opportunities Programme (UROP) student research projects, and 1 group project (5 students) on data poisoning attacks against machine learning.

 
 
 
 
 

Intern, Data Engineering

Santander Digital Services

Nov 2017 – Feb 2018 Madrid, Spain
Hired by the Data Science Talent Program at Santander Group. Carried out Extract, Transform, Load (ETL) tasks in the Area of Big Data and BI Solutions, in the data lake of the company:

  • Study and optimization of a PoC, written in Java language, for the extraction of information from a database warehoused in Hive/Impala (through Hue), and its subsequent transmission, processing and visualisation in Kibana. Other involved technologies were: Apache Maven, Apache Spark, MapReduce, and HDFS.
  • Collaboration in a data migration project: execution, validation and optimization of processes and SQL queries to ETL data warehoused in Hive/Impala (through Hue), according to a pre-established mesh (Control-M).
 
 
 
 
 

Research Assistant, RF, Antennas, and Sensors

Universidad Carlos III de Madrid

Feb 2016 – Oct 2017 Madrid, Spain

Research in antennas, passive electromagnetic sensors, and IoT applications in the Dept. of Signal Theory and Communications.

We proposed a novel low-cost and portable IoT reader for passive wireless electromagnetic sensors. An interesting application is the remote measurement of harmful substances. To our knowledge, it was the first wireless reader of passive electromagnetic sensors including IoT functionalities (“An IoT Reader for Wireless Passive Electromagnetic Sensors”).

We also designed a novel contactless sensing system composed of a metamaterial-inspired sensor and a reader antenna, in order to detect substances in short distances in real time. This led to a low-cost, replaceable, battery-free and fully passive solution. Moreover, thanks to the short-reading range, the sensor avoids external interferences and undesired radiations (“"A Contactless Dielectric Constant Sensing System Based on a Split-Ring Resonator-Loaded Monopole”; “A Contactless System for the Dielectric Characterization of Liquid Drops”).

We also collaborated with an important Spanish telecommunications company (Prodetel, S.A.) in an R&D project. We designed an innovative multiband feeder for aeronautic telemetry applications.

 
 
 
 
 

Private Tutor

Self-employed

Jul 2014 – Aug 2015 Madrid, Spain
  • Electrical Networks and Electronics: Undergraduate students.
  • Mathematics: Secondary school students.

Skills

Machine Learning

80%

Adversarial Machine Learning

80%

Data Poisoning

90%

Federated Learning

70%

Deep Learning

70%

GANs

80%

Python

80%

NumPy

80%

Scikit-learn

70%

PyTorch

80%

TensorFlow

60%

Keras

50%

MATLAB

80%

Java

50%

C

50%

LaTeX

80%

SQL

40%

RF and Antenna Engineering

80%

RADAR

80%

International Experience

80%

Spanish

100%

English

80%

Mentoring

 
 
 
 
 

Mentor, COIT Ment-it

Colegio Oficial de Ingenieros de Telecomunicación (Spain)

Jan 2023 – Present
Advising Telecommunications Engineers on their careers, future plans, and necessary skills and competences.
 
 
 
 
 

PhD Buddy, Department of Computing

Imperial College London

Jan 2022 – Present
Advising new PhD students on PhD life, student-supervisor relationships, time management and any other issues during the PhD stage.
 
 
 
 
 

Alumni Mentor

Universidad Carlos III de Madrid

Jan 2022 – Present
Advising UC3M students on their careers, future plans, and necessary skills and competences.
 
 
 
 
 

Assistant Supervisor

Imperial College London

Jan 2018 – Dec 2022
Assisted in the supervision of 2 MSc (one of them passed with Distinction), 1 MEng, and 1 UROP student research projects, and 1 group project (5 students) on data poisoning attacks against machine learning.

Selected R&D Projects

Machine Unlearning under Data Poisoning

Evaluating the Robustness of Machine Learning Algorithms in Adversarial Settings (ERASE)

Development of a Multiband Feeder with Autotracking Capability

Designed an innovative multiband feeder with autotracking capability for aeronautic telemetry applications. Concretely, we conceived a patch antenna array in order to feed a parabolic reflector working simultaneously in the S and C frequency bands. This system is expected to provide an error signal that will allow tracking the trajectory of a particular target (autotracking).

Design of a Reading System for Metamaterial-Based Passive Wireless Sensors

In this project, a low-cost and portable wireless reading system for passive sensors is designed and manufactured. The reader interrogates the metamaterial-based sensors within a short-range radio link, avoiding the direct contact with the substances under test. It is demonstrated, through the wireless measurement of different liquids, that the proposed system can estimate their dielectric permittivity, obtaining an accurate linear approximation.

Talks

Defense Against the Dark Arts: Machine Learning Models Can Be Easily Poisoned

Machine Learning Models Can Be Easily Poisoned (But Not All Is Lost)

Awards and Grants

Top Talent

Nova is a global top talent network where all members (from +72 countries) accelerate their careers through a meticulous selection process that verifies that each member belongs to the top 3% in their respective field of expertise.

Alumni Excellence Award

Awarded to graduates from Universidad Carlos III de Madrid with accredited excellence in their professional development.

35 under 35 List

This lists brings together 35 potential and consolidated minds of 35 or less years of age which are experts on the global digital order, specially focusing on algorithmic governance and AI.

Best Poster Award

Awarded to the poster “Regularisation Can Mitigate Poisoning Attacks: A Novel Analysis Based on Multiobjective Bilevel Optimisation”.

PhD Scholarship

Competitive call.

MSc Research Scholarship

Competitive call.

Top 7% of the BEng in Telecommunications Engineering

Tuition-fee Scholarships

Merit and need-based scholarships.

Honors Diploma in Secondary Education

Awarded to the best secondary school students of the Community of Madrid (Spain).

Contact

  • j (dot) cano (at) imperial (dot) ac (dot) uk
  • 180 Queen's Gate, London, SW7 2AZ
  • DM me