On the Impossibility of Separating Intelligence from Judgment: The Computational Intractability of Filtering for AI Alignment

With the increased deployment of large language models (LLMs), one concern is their potential misuse for generating harmful content. Our work studies the alignment challenge, with a focus on filters to prevent the generation of unsafe information. Two natural points of intervention are the filtering of the input prompt before it reaches the model, and filtering the output after generation. Our main results demonstrate computational challenges in filtering both prompts and outputs. First, we show that there exist LLMs for which there are no efficient prompt filters: adversarial prompts that elicit harmful behavior can be easily constructed, which are computationally indistinguishable from benign prompts for any efficient filter. Our second main result identifies a natural setting in which output filtering is computationally intractable. All of our separation results are under cryptographic hardness assumptions. In addition to these core findings, we also formalize and study relaxed mitigation approaches, demonstrating further computational barriers. We conclude that safety cannot be achieved by designing filters external to the LLM internals (architecture and weights); in particular, black-box access to the LLM will not suffice. Based on our technical results, we argue that an aligned AI system's intelligence cannot be separated from its judgment.

A Cryptographic Perspective on Mitigation vs. Detection in Machine Learning

In this paper, we initiate a cryptographically inspired theoretical study of detection versus mitigation of adversarial inputs produced by attackers of Machine Learning algorithms during inference time. We formally define defense by detection (DbD) and defense by mitigation (DbM). Our definitions come in the form of a 3-round protocol between two resource-bounded parties: a trainer/defender and an attacker. The attacker aims to produce inference-time inputs that fool the training algorithm. We define correctness, completeness, and soundness properties to capture successful defense at inference time while not degrading (too much) the performance of the algorithm on inputs from the training distribution. We first show that achieving DbD and achieving DbM are equivalent for ML classification tasks. Surprisingly, this is not the case for ML generative learning tasks, where there are many possible correct outputs that can be generated for each input. We show a separation between DbD and DbM by exhibiting a generative learning task for which is possible to defend by mitigation but is provably impossible to defend by detection under the assumption that the Identity-Based Fully Homomorphic Encryption (IB-FHE), publicly-verifiable zero-knowledge Succinct Non-Interactive Arguments of Knowledge (zk-SNARK) and Strongly Unforgeable Signatures exist. The mitigation phase uses significantly fewer samples than the initial training algorithm.