Adversaries Can Misuse Combinations of Safe Models
June 20, 2024 Β· Declared Dead Β· π International Conference on Machine Learning
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Erik Jones, Anca Dragan, Jacob Steinhardt
arXiv ID
2406.14595
Category
cs.CR: Cryptography & Security
Cross-listed
cs.AI,
cs.LG
Citations
21
Venue
International Conference on Machine Learning
Last Checked
4 months ago
Abstract
Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that individually testing models for misuse is inadequate; adversaries can misuse combinations of models even when each individual model is safe. The adversary accomplishes this by first decomposing tasks into subtasks, then solving each subtask with the best-suited model. For example, an adversary might solve challenging-but-benign subtasks with an aligned frontier model, and easy-but-malicious subtasks with a weaker misaligned model. We study two decomposition methods: manual decomposition where a human identifies a natural decomposition of a task, and automated decomposition where a weak model generates benign tasks for a frontier model to solve, then uses the solutions in-context to solve the original task. Using these decompositions, we empirically show that adversaries can create vulnerable code, explicit images, python scripts for hacking, and manipulative tweets at much higher rates with combinations of models than either individual model. Our work suggests that even perfectly-aligned frontier systems can enable misuse without ever producing malicious outputs, and that red-teaming efforts should extend beyond single models in isolation.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Cryptography & Security
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
The Limitations of Deep Learning in Adversarial Settings
R.I.P.
π»
Ghosted
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
R.I.P.
π»
Ghosted
Spectre Attacks: Exploiting Speculative Execution
R.I.P.
π»
Ghosted
How To Backdoor Federated Learning
R.I.P.
π»
Ghosted
Evasion Attacks against Machine Learning at Test Time
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted