Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Mohamed Amine Merzouk
Observed name:
Merzouk, Mohamed Amine
Institutions:
Mila - Quebec Artificial Intelligence Institute,
McGill University
Observed institutions:
Institut de Recherche Technologique SystemX,
IMT Atlantique,
École Nationale Supérieure d'Informatique,
Mila - Quebec Artificial Intelligence Institute,
Polytechnique Montréal,
McGill University
show all 6
ORCID:
0000-0002-8016-6806
Observed ORCID:
0000-0002-8016-6806
OpenAlex ID:
A5042550145
Investigating the practicality of adversarial evasion attacks on network intrusion detection
2022
·
Mohamed Amine Merzouk
, Frédéric Cuppens
, et al.
·
Annals of Telecommunications
·
47
Adversarial robustness of deep reinforcement learning-based intrusion detection
2024
·
Mohamed Amine Merzouk
, Christopher Neal
, et al.
·
International Journal of Information Security
·
28
A Deeper Analysis of Adversarial Examples in Intrusion Detection
2021
·
Mohamed Amine Merzouk
, Frédéric Cuppens
, et al.
·
Lecture notes in computer science
·
12
Diffusion-Based Adversarial Purification for Intrusion Detection
2025
·
Mohamed Amine Merzouk
, Erwan Beurier
, et al.
·
Lecture notes in computer science
·
11
PDF
Evading Deep Reinforcement Learning-based Network Intrusion Detection with Adversarial Attacks
2022
·
Mohamed Amine Merzouk
, Joséphine Delas
, et al.
·
International Conference on Availability, Reliability and Security (ARES)
·
11
Quantifying Overclaiming Propensity in Frontier LLM Agents
2026
·
Smyth, Nolan
, Mantilla-Ramos, Yorguin-Jose
, et al.
·
arXiv (Cornell University)
·
10
PDF
Parameterizing poisoning attacks in federated learning-based intrusion detection
2023
·
Mohamed Amine Merzouk
, Frédéric Cuppens
, et al.
·
International Conference on Availability, Reliability and Security (ARES)
·
10
PDF
Efficiency at What Cost? Safety and Fairness in Parameter-Efficient Fine-Tuning of LLMs
2026
·
Mina Taraghi
, Yann Pequignot
, et al.
·
IEEE Transactions on Artificial Intelligence
·
4
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
2026
·
Merzouk, Mohamed Amine
, Carpov, Dmitri
, et al.
·
arXiv (Cornell University)
·
2
PDF
Efficient Safety Alignment of Language Models via Latent Personality Traits
2026
·
Merzouk, Mohamed Amine
, Smyth, Nolan
, et al.
·
arXiv (Cornell University)
·
1
PDF
GrayShield: Bit-Level Sanitization for Transformer Model Supply-Chain Security
2026
·
Foundjem, Armstrong
, Chuang, Tsung-Hsien
, et al.
·
arXiv (Cornell University)
PDF
Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
2026
·
Le, Linh
, Williams-King, David
, et al.
·
arXiv (Cornell University)
PDF
Show more works
View as search
Works count:
13
Citation count:
136
H-index:
7
I10-index:
7
Year
Topic
Type
