Nicolas Chapados
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Nicolas Chapados has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Quentin Cappart
UCLouvain, Louvain-la-Neuve, Belgium
2 shared publications - Abhay Puri
ServiceNow Research, Montreal, QC, Canada
1 shared publication - Alexandre Drouin
Department of Computer Science and Software Engineering, Université Laval, Québec, Canada
1 shared publication - Alexandre Lacoste
ServiceNow Research, Montreal, QC, Canada
1 shared publication - Ana Marasović
University of Utah, Salt Lake City, USA
1 shared publication - Chandra Kiran Reddy Evuru
Servicenow, Santa Clara, CA, USA
1 shared publication
Latest Publications
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 4491-4510
Societal Frameworks Can Improve LLM Alignment
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 4491-4510
Open AccessSocietal Frameworks Can Improve LLM Alignment
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 755-772
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
While finetuning AI agents on interaction data—such as web browsing or tool use—improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can effectively poison the data collection pipeline at multiple stages to embed hard-to-detect backdoors that, when triggered, cause unsafe or malicious behavior. We formalize three realistic threat models across distinct layers of the supply chain: direct poisoning of finetuning data, pre-backdoored base models, and environment poisoning, a novel attack vector that exploits vulnerabilities specific to agentic training pipelines. Evaluated on two widely adopted agentic benchmarks, all three threat models prove effective: poisoning only a small number of demonstrations is sufficient to embed a backdoor that causes an agent to leak confidential user information with over 80% success. Furthermore, we demonstrate that prominent safeguards, including four guardrail models and one weight-based defense, fail to detect or prevent the malicious behavior. These findings expose an urgent and underexplored threat to agentic AI development, underscoring the need for rigorous security vetting of data collection pipelines and model supply chains.
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 755-772
Open AccessMalice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
While finetuning AI agents on interaction data—such as web browsing or tool use—improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can effectively poison the data collection pipeline at multiple stages to embed hard-to-detect backdoors that, when triggered, cause unsafe or malicious behavior. We formalize three realistic threat models across distinct layers of the supply chain: direct poisoning of finetuning data, pre-backdoored base models, and environment poisoning, a novel attack vector that exploits vulnerabilities specific to agentic training pipelines. Evaluated on two widely adopted agentic benchmarks, all three threat models prove effective: poisoning only a small number of demonstrations is sufficient to embed a backdoor that causes an agent to leak confidential user information with over 80% success. Furthermore, we demonstrate that prominent safeguards, including four guardrail models and one weight-based defense, fail to detect or prevent the malicious behavior. These findings expose an urgent and underexplored threat to agentic AI development, underscoring the need for rigorous security vetting of data collection pipelines and model supply chains.
- 1 January 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Optimization
- Vol. 6 (1) , 1-18
Dynamic Routing and Wavelength Assignment with Reinforcement Learning
With the rapid developments in communication systems, and considering their dynamic nature, all-optical networks are becoming increasingly complex. This study proposes a novel method based on deep reinforcement learning for the routing and wavelength assignment problem in all-optical wavelength-decision-multiplexing networks. We consider dynamic incoming requests, in which their arrival and holding times are not known in advance. The objective is to devise a strategy that minimizes the number of rejected packages due to the lack of resources in the long term. We use graph neural networks to capture crucial latent information from the graph-structured input to develop the optimal strategy. The proposed deep reinforcement learning algorithm selects a route and a wavelength simultaneously for each incoming traffic connection as they arrive. The results demonstrate that the learned agent outperforms the methods used in practice and can be generalized on network topologies that did not participate in training.
- 1 January 2024
- Published by Institute for Operations Research and the Management Sciences (INFORMS) in INFORMS Journal on Optimization
- Vol. 6 (1) , 1-18
Dynamic Routing and Wavelength Assignment with Reinforcement Learning
With the rapid developments in communication systems, and considering their dynamic nature, all-optical networks are becoming increasingly complex. This study proposes a novel method based on deep reinforcement learning for the routing and wavelength assignment problem in all-optical wavelength-decision-multiplexing networks. We consider dynamic incoming requests, in which their arrival and holding times are not known in advance. The objective is to devise a strategy that minimizes the number of rejected packages due to the lack of resources in the long term. We use graph neural networks to capture crucial latent information from the graph-structured input to develop the optimal strategy. The proposed deep reinforcement learning algorithm selects a route and a wavelength simultaneously for each incoming traffic connection as they arrive. The results demonstrate that the learned agent outperforms the methods used in practice and can be generalized on network topologies that did not participate in training.