Jianwei Chi

Yiming Zhang, Jianfeng Chi, Hailey Nguyen et al.

Text generation has a fundamental limitation almost by definition: there is no taking back tokens that have been generated, even when they are clearly problematic. In the context of language model safety, when a partial unsafe generation is produced, language models by their nature tend to happily keep on generating similarly unsafe additional text. This is in fact how safety alignment of frontier models gets circumvented in the wild, despite great efforts in improving their safety. Deviating from the paradigm of approaching safety alignment as prevention (decreasing the probability of harmful responses), we propose backtracking, a technique that allows language models to "undo" and recover from their own unsafe generation through the introduction of a special [RESET] token. Our method can be incorporated into either SFT or DPO training to optimize helpfulness and harmlessness. We show that models trained to backtrack are consistently safer than baseline models: backtracking Llama-3-8B is four times more safe than the baseline model (6.1\% $\to$ 1.5\%) in our evaluations without regression in helpfulness. Our method additionally provides protection against four adversarial attacks including an adaptive attack, despite not being trained to do so.

Yiming Zhang, Javier Rando, Ivan Evtimov et al. · eth-zurich

Large language models are pre-trained on uncurated text datasets consisting of trillions of tokens scraped from the Web. Prior work has shown that: (1) web-scraped pre-training datasets can be practically poisoned by malicious actors; and (2) adversaries can compromise language models after poisoning fine-tuning datasets. Our work evaluates for the first time whether language models can also be compromised during pre-training, with a focus on the persistence of pre-training attacks after models are fine-tuned as helpful and harmless chatbots (i.e., after SFT and DPO). We pre-train a series of LLMs from scratch to measure the impact of a potential poisoning adversary under four different attack objectives (denial-of-service, belief manipulation, jailbreaking, and prompt stealing), and across a wide range of model sizes (from 600M to 7B). Our main result is that poisoning only 0.1% of a model's pre-training dataset is sufficient for three out of four attacks to measurably persist through post-training. Moreover, simple attacks like denial-of-service persist through post-training with a poisoning rate of only 0.001%.