Urgent! Internships on hardware/microarchitectural security of deep/machine learning implementations Job | INRIA
Contexte et atouts du poste
The internships are expected to start around February/March and extend for up to 6 months
Scientific context
After more than 20 years of research, Side-Channel Attacks (SCA) are still one of the most critical vulnerabilities in embedded systems.
SCAs exploit correlations between processed data and physical, observable side effects of computing – power consumption, electromagnetic (EM) emanations, or timing, to name a few – to extract sensitive information.
Traditionally directed to retrieve the cryptographic key of mathematically secure cryptographic implementations, the increasing adoption of Machine Learning (ML) and Deep Learning (DL) is making Artificial Intelligence (AI) a new target.
As these systems increasingly deal with sensitive data and control critical infrastructure, and as new vulnerabilities are reported, the hardware/software security of ML/DL systems is emerging as a key cybersecurity concern to build trustworthy AI-based systems [1, 2].
Side-channel attacks on DL implementations pave the way to attacks aiming at stealing the intellectual property of DL-based products/services [3, 4], violating the privacy of the end-user, and facilitating attacks on DL-based systems.
References
[1] S.
Mittal, H.
Gupta, and S.
Srivastava.
“A Survey on Hardware Security of DNN Models and Accelerators”.
J.
Syst.
Archit.
117 2021, p.
102163.
doi: 10.1016/j.sysarc.2021.102163.
[2] V.
Meyers, D.
Gnad, and M.
Tahoori.
“Active and Passive Physical Attacks on Neural Network Accelerators”.
IEEE Design & Test 2023, pp.
1–1.
doi: 10.1109/MDAT.2023.3253603.
[3] M.
Méndez Real and R.
Salvador.
“Physical Side-Channel Attacks on Embedded Neural Networks: A Survey”.
Appl.
Sci.
11 15, 2021, p.
6790.
doi: 10.3390/app11156790.
[4] P.
Horváth, D.
Lauret, Z.
Liu, and L.
Batina.
“SoK: Neural Network Extraction Through Physical Side Channels”.
33rd USENIX Security Symposium (USENIX Security 24).
2024, pp.
3403–3422.
[5] M.
Isakov, V.
Gadepally, K.
M.
Gettings, and M.
A.
Kinsy.
“Survey of Attacks and Defenses on Edge-Deployed
Neural Networks”.
IEEE HPEC.
2019, pp.
1–8.
doi: 10.1109/HPEC.2019.8916519.
[6] L.
Batina, S.
Bhasin, D.
Jap, and S.
Picek.
“CSI NN: Reverse Engineering of Neural Network Architectures
Through Electromagnetic Side Channel”.
USENIX Security Symp.
2019, pp.
515–532.
[7] R.
Joud, P.-A.
Moëllic, S.
Pontié, and J.-B.
Rigaud.
“A Practical Introduction to Side-Channel Extraction of Deep
Neural Network Parameters”.
Smart Card Research and Advanced Applications.
Ed. by I.
Buhan and T.
Schneider.
Cham: Springer International Publishing, 2023, pp.
45–65.
doi: 10.1007/978-3-031-25319-5_3.
[8] R.
Joud, P.-A.
Moëllic, S.
Pontié, and J.-B.
Rigaud.
“Like an Open Book?
Read Neural Network Architecture
with Simple Power Analysis on 32-Bit Microcontrollers”.
Smart Card Research and Advanced Applications.
Ed. by
S.
Bhasin and T.
Roche.
Cham: Springer Nature Switzerland, 2024, pp.
256–276.
doi: 10.1007/978- 3- 031-
54409-5_13.
[9] Y.
Zhang, R.
Yasaei, H.
Chen, Z.
Li, and M.
A.
A.
Faruque.
“Stealing Neural Network Structure Through Remote
FPGA Side-Channel Analysis”.
IEEE Trans.
Inf.
Forensics Secur.
16 2021, pp.
4377–4388.
doi: 10.1109/TIFS.
2021.3106169.
[10] S.
Moini, S.
Tian, D.
Holcomb, J.
Szefer, and R.
Tessier.
“Power Side-Channel Attacks on BNN Accelerators in
Remote FPGAs”.
IEEE J.
Emerg.
Sel.
Top.
Circuits Syst.
11.2 2021, pp.
357–370.
doi: 10.1109/JETCAS.2021.
3074608.
Mission confiée
These internships are framed in the ANR JCJC project ATTILA1 (young investigators' grant from the French national research agency).
The objectives are to investigate the susceptibility of DL-based systems to side-channel attacks and to design SCA-secure DL implementations.
In these internships, we are interested in both local SCA attacks on edge devices, highly exposed to attackers [5–8], and remote SCA attacks on cloud-based DL implementations [9, 10].
The internships cover both software implementations (e.g., in microcontrollers) and hardware implementations (e.g., accelerators in FPGA) of DL algorithms.
Although the main focus is on physical side-channel vulnerabilities (e.g., power consumption or EM emanations), we are open to exploring microarchitectural timing side channels exposing, e.g., cache, DRAM, or other processor microarchitecture vulnerabilities.
This position offers a good opportunity to discover an emerging topic and gain skills to help you complete a PhD in the field of (AI) hardware/microarchitecture security.
Principales activités
Depending on the background of the candidates, the internships can take different directions, such as DNN implementations in FPGA or microcontrollers using AxC techniques, evaluation of DNN side-channel security, and implementation and evaluation of countermeasures.
Compétences
You should have a strong background in (at least) one of the following topics:
Other interesting technical skills include:
Languages: You can speak, write, and read English at a professional level (french language is not required).
Avantages
✨ Smart • Intelligent • Private • Secure
Practice for Any Interview Q&A (AI Enabled)
Predict interview Q&A (AI Supported)
Mock interview trainer (AI Supported)
Ace behavioral interviews (AI Powered)
Record interview questions (Confidential)
Master your interviews
Track your answers (Confidential)
Schedule your applications (Confidential)
Create perfect cover letters (AI Supported)
Analyze your resume (NLP Supported)
ATS compatibility check (AI Supported)
Optimize your applications (AI Supported)
O*NET Supported
O*NET Supported
O*NET Supported
O*NET Supported
O*NET Supported
European Union Recommended
Institution Recommended
Institution Recommended
Researcher Recommended
IT Savvy Recommended
Trades Recommended
O*NET Supported
Artist Recommended
Researchers Recommended
Create your account
Access your account
Create your professional profile
Preview your profile
Your saved opportunities
Reviews you've given
Companies you follow
Discover employers
O*NET Supported
Common questions answered
Help for job seekers
How matching works
Customized job suggestions
Fast application process
Manage alert settings
Understanding alerts
How we match resumes
Professional branding guide
Increase your visibility
Get verified status
Learn about our AI
How ATS ranks you
AI-powered matching
Join thousands of professionals who've advanced their careers with our platform
Unlock Your Internships on Potential: Insight & Career Growth Guide
Real-time Internships on Jobs Trends in Rennes, France (Graphical Representation)
Explore profound insights with Expertini's real-time, in-depth analysis, showcased through the graph below. This graph displays the job market trends for Internships on in Rennes, France using a bar chart to represent the number of jobs available and a trend line to illustrate the trend over time. Specifically, the graph shows 182 jobs in France and 3 jobs in Rennes. This comprehensive analysis highlights market share and opportunities for professionals in Internships on roles. These dynamic trends provide a better understanding of the job market landscape in these regions.
Great news! INRIA is currently hiring and seeking a Internships on hardware/microarchitectural security of deep/machine learning implementations to join their team. Feel free to download the job details.
Wait no longer! Are you also interested in exploring similar jobs? Search now: Internships on hardware/microarchitectural security of deep/machine learning implementations Jobs Rennes.
An organization's rules and standards set how people should be treated in the office and how different situations should be handled. The work culture at INRIA adheres to the cultural norms as outlined by Expertini.
The fundamental ethical values are:The average salary range for a Internships on hardware/microarchitectural security of deep/machine learning implementations Jobs France varies, but the pay scale is rated "Standard" in Rennes. Salary levels may vary depending on your industry, experience, and skills. It's essential to research and negotiate effectively. We advise reading the full job specification before proceeding with the application to understand the salary package.
Key qualifications for Internships on hardware/microarchitectural security of deep/machine learning implementations typically include Computer Occupations and a list of qualifications and expertise as mentioned in the job specification. Be sure to check the specific job listing for detailed requirements and qualifications.
To improve your chances of getting hired for Internships on hardware/microarchitectural security of deep/machine learning implementations, consider enhancing your skills. Check your CV/Résumé Score with our free Resume Scoring Tool. We have an in-built Resume Scoring tool that gives you the matching score for each job based on your CV/Résumé once it is uploaded. This can help you align your CV/Résumé according to the job requirements and enhance your skills if needed.
Here are some tips to help you prepare for and ace your job interview:
Before the Interview:To prepare for your Internships on hardware/microarchitectural security of deep/machine learning implementations interview at INRIA, research the company, understand the job requirements, and practice common interview questions.
Highlight your leadership skills, achievements, and strategic thinking abilities. Be prepared to discuss your experience with HR, including your approach to meeting targets as a team player. Additionally, review the INRIA's products or services and be prepared to discuss how you can contribute to their success.
By following these tips, you can increase your chances of making a positive impression and landing the job!
Setting up job alerts for Internships on hardware/microarchitectural security of deep/machine learning implementations is easy with Rennes | Expertini. Simply visit our job alerts page here, enter your preferred job title and location, and choose how often you want to receive notifications. You'll get the latest job openings sent directly to your email for FREE!
