Publications & Manuscripts

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Xiangyu Qi*, Yi Zeng*, Tinghao Xie*, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal$^†$, Peter Henderson$^†$
[pdf] [project website] Preprint (Under Review)

📰This work was exclusively reported by New York Times and many other social medias!

Optimizing large language models (LLMs) for downstream use cases often involves the customization of pre-trained LLMs through further fine-tuning. Meta’s open release of Llama models and OpenAI’s APIs for fine-tuning GPT-3.5 Turbo on custom datasets also encourage this practice. But, what are the safety costs associated with such custom fine-tuning? We note that while existing safety alignment infrastructures can restrict harmful behaviors of LLMs at inference time, they do not cover safety risks when fine-tuning privileges are extended to end-users. Our red teaming studies find that the safety alignment of LLMs can be compromised by fine-tuning with only a few adversarially designed training examples. For instance, we jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 such examples at a cost of less than $0.20 via OpenAI’s APIs, making the model responsive to nearly any harmful instructions. Disconcertingly, our research also reveals that, even without malicious intent, simply fine-tuning with benign and commonly used datasets can also inadvertently degrade the safety alignment of LLMs, though to a lesser extent. These findings suggest that fine-tuning aligned LLMs introduces new safety risks that current safety infrastructures fall short of addressing — even if a model’s initial safety alignment is impeccable, it is not necessarily to be maintained after custom fine-tuning. We outline and critically analyze potential mitigations and advocate for further research efforts toward reinforcing safety protocols for the custom fine-tuning of aligned LLMs.

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

Tinghao Xie, Xiangyu Qi, Ping He, Yiming Li, Jiachen T. Wang, Prateek Mittal
[pdf] Preprint (Under Review)

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that operate independently of how the model was generated. The proposed defense is built upon a novel reverse engineering approach that can directly extract backdoor functionality of a given backdoored model to a backdoor expert model. The approach is straightforward – finetuning the backdoored model over a small set of intentionally mislabeled clean samples, such that it unlearns the normal functionality while still preserving the backdoor functionality, and thus resulting in a model (dubbed a backdoor expert model) that can only recognize backdoor inputs. Based on the extracted backdoor expert model, we show the feasibility of devising highly accurate backdoor input detectors that filter out the backdoor inputs during model inference. Further augmented by an ensemble strategy with a finetuned auxiliary model, our defense, BaDExpert (Backdoor Input Detection with Backdoor Expert), effectively mitigates 16 SOTA backdoor attacks while minimally impacting clean utility. The effectiveness of BaDExpert has been verified on multiple datasets (CIFAR10, GTSRB and ImageNet) across various model architectures (ResNet, VGG, MobileNetV2 and Vision Transformer).

Towards A Proactive ML Approach for Detecting Backdoor Poison Samples

Xiangyu Qi, Tinghao Xie, Jiachen T. Wang, Tong Wu, Saeed Mahloujifar, Prateek Mittal
[pdf] USENIX Security 2023

We suggest a proactive backdoor defense paradigm in which defenders engage proactively with the entire model training and poison detection pipeline, directly enforcing and magnifying distinctive characteristics of the post-attacked model to facilitate poison detection. We introduce the technique of Confusion Training (CT) as a concrete instantiation of our framework. CT applies an additional poisoning attack to the already poisoned dataset, actively decoupling benign correlation while exposing backdoor patterns to detection.

Ensemble of Narrow DNN Chains

Tinghao Xie
[pdf] Manuscript (Course Essay for Machine Learning at the University of Oxford), 2021

We propose the extremely small Ensemble of Narrow DNN Chains (ENDC) framework.