Advances in real-world adversarial threats have heightened concerns over the privacy and security of AI systems. One key threat is Data Poisoning, where malicious data is injected into training sets or model inputs to compromise model behavior. While much of the current research focuses on deep learning, particularly Foundation Models such as Large Language Models, there is limited understanding of how data poisoning affects different model eras. This survey presents a comparative analysis of data poisoning vulnerabilities in different model eras: statistical machine learning models, smaller-scale ”classical” deep learning models, and foundation models. Our goal is to inform practitioners of the trade-offs between robustness and performance when choosing models for different applications.
Jia Yi Chan, Huaqun Guo, Timothy Liu et al.· Singapore Institute of Techn...· 0 citations
Advances in real-world adversarial threats have heightened concerns over the privacy and security of AI systems. One key threat is Data Poisoning, where malicious data is injected into training sets or model inputs to compromise model behavior. While much of the current research focuses on deep learning, particularly Foundation Models such as Large Language Models, there is limited understanding of how data poisoning affects different model eras. This survey presents a comparative analysis of data poisoning vulnerabilities in different model eras: statistical machine learning models, smaller-scale ”classical” deep learning models, and foundation models. Our goal is to inform practitioners of the trade-offs between robustness and performance when choosing models for different applications.
Jia Yi Chan, Huaqun Guo, Timothy Liu et al.· Singapore Institute of Techn...· 0 citations
With the increase in adoption of Generative AI (GenAI) and Large Language Models (LLMs), concerns on their security, such as prompt injection and unauthorised model behaviour, arise. These pose significant risks to data confidentiality, system integrity, and user trust. To counter this, this project presents LMAO (Language Model Anomaly Observer), a behavioural monitoring framework which incorporates AI/ML and telemetry-based analysis to detect abnormal actions displayed by GenAI models.
Wei Xin Lai, Hui Li Tay, Timothy Cun Kiat See et al.· Singapore Institute of Techn...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
