#MLSecOps
"Fewer Weights, More Problems: A Practical Attack on LLM Pruning", 2025.
]-> Repo + threat model
// Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of LLMs during inference. While the utility and efficiency of pruning methods have improved significantly, the security implications of pruning remain underexplored. In this work, for the first time, we show that modern LLM pruning methods can be maliciously exploited. In particular, an adversary can construct a model that appears benign yet, once pruned, exhibits malicious behaviors
Post #1653
140