Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

We show that even the most recent safety-aligned LLMs are not robust to simple adaptive jailbreaking attacks. First, we demonstrate how to successfully leverage access to logprobs for jailbreaking: we initially design an adversarial prompt template (sometimes adapted to the target LLM), and then we apply random search on a suffix to maximize the target logprob (e.g., of the token "Sure"), potentially with multiple restarts. In this way, we achieve nearly 100\% attack success rate -- according to GPT-4 as a judge -- on GPT-3.5/4, Llama-2-Chat-7B/13B/70B, Gemma-7B, and R2D2 from HarmBench that was adversarially trained against the GCG attack. We also show how to jailbreak all Claude models -- that do not expose logprobs -- via either a transfer or prefilling attack with 100\% success rate. In addition, we show how to use random search on a restricted set of tokens for finding trojan strings in poisoned models -- a task that shares many similarities with jailbreaking -- which is the algorithm that brought us the first place in the SaTML'24 Trojan Detection Competition. The common theme behind these attacks is that adaptivity is crucial: different models are vulnerable to different prompting templates (e.g., R2D2 is very sensitive to in-context learning prompts), some models have unique vulnerabilities based on their APIs (e.g., prefilling for Claude), and in some settings it is crucial to restrict the token search space based on prior knowledge (e.g., for trojan detection). We provide the code, prompts, and logs of the attacks at https://github.com/tml-epfl/llm-adaptive-attacks.

JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Jailbreak attacks cause large language models (LLMs) to generate harmful, unethical, or otherwise objectionable content. Evaluating these attacks presents a number of challenges, which the current collection of benchmarks and evaluation techniques do not adequately address. First, there is no clear standard of practice regarding jailbreaking evaluation. Second, existing works compute costs and success rates in incomparable ways. And third, numerous works are not reproducible, as they withhold adversarial prompts, involve closed-source code, or rely on evolving proprietary APIs. To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) a new jailbreaking dataset containing 100 unique behaviors, which we call JBB-Behaviors; (2) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (3) a standardized evaluation framework that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard that tracks the performance of attacks and defenses for various LLMs. We have carefully considered the potential ethical implications of releasing this benchmark, and believe that it will be a net positive for the community. Over time, we will expand and adapt the benchmark to reflect technical and methodological advances in the research community.

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning

There is a consensus that instruction fine-tuning of LLMs requires high-quality data, but what are they? LIMA (NeurIPS 2023) and AlpaGasus (ICLR 2024) are state-of-the-art methods for selecting such high-quality examples, either via manual curation or using GPT-3.5-Turbo as a quality scorer. We show that the extremely simple baseline of selecting the 1,000 instructions with longest responses from standard datasets can consistently outperform these sophisticated methods according to GPT-4 and PaLM-2 as judges, while remaining competitive on the OpenLLM benchmarks that test factual knowledge. We demonstrate this for several state-of-the-art LLMs (Llama-2-7B, Llama-2-13B, and Mistral-7B) and datasets (Alpaca-52k and Evol-Instruct-70k). In addition, a lightweight refinement of such long instructions can further improve the abilities of the fine-tuned LLMs, and allows us to obtain the 2nd highest-ranked Llama-2-7B-based model on AlpacaEval 2.0 while training on only 1,000 examples and no extra preference data. We also conduct a thorough analysis of our models to ensure that their enhanced performance is not simply due to GPT-4's preference for longer responses, thus ruling out any artificial improvement. In conclusion, our findings suggest that fine-tuning on the longest instructions should be the default baseline for any research on instruction fine-tuning.

Scaling Compute Is Not All You Need for Adversarial Robustness

The last six years have witnessed significant progress in adversarially robust deep learning. As evidenced by the CIFAR-10 dataset category in RobustBench benchmark, the accuracy under $\ell_\infty$ adversarial perturbations improved from 44\% in \citet{Madry2018Towards} to 71\% in \citet{peng2023robust}. Although impressive, existing state-of-the-art is still far from satisfactory. It is further observed that best-performing models are often very large models adversarially trained by industrial labs with significant computational budgets. In this paper, we aim to understand: ``how much longer can computing power drive adversarial robustness advances?" To answer this question, we derive \emph{scaling laws for adversarial robustness} which can be extrapolated in the future to provide an estimate of how much cost we would need to pay to reach a desired level of robustness. We show that increasing the FLOPs needed for adversarial training does not bring as much advantage as it does for standard training in terms of performance improvements. Moreover, we find that some of the top-performing techniques are difficult to exactly reproduce, suggesting that they are not robust enough for minor changes in the training setup. Our analysis also uncovers potentially worthwhile directions to pursue in future research. Finally, we make our benchmarking framework (built on top of \texttt{timm}~\citep{rw2019timm}) publicly available to facilitate future analysis in efficient robust deep learning.

The Effects of Overparameterization on Sharpness-aware Minimization: An Empirical and Theoretical Analysis

Training an overparameterized neural network can yield minimizers of the same level of training loss and yet different generalization capabilities. With evidence that indicates a correlation between sharpness of minima and their generalization errors, increasing efforts have been made to develop an optimization method to explicitly find flat minima as more generalizable solutions. This sharpness-aware minimization (SAM) strategy, however, has not been studied much yet as to how overparameterization can actually affect its behavior. In this work, we analyze SAM under varying degrees of overparameterization and present both empirical and theoretical results that suggest a critical influence of overparameterization on SAM. Specifically, we first use standard techniques in optimization to prove that SAM can achieve a linear convergence rate under overparameterization in a stochastic setting. We also show that the linearly stable minima found by SAM are indeed flatter and have more uniformly distributed Hessian moments compared to those of SGD. These results are corroborated with our experiments that reveal a consistent trend that the generalization improvement made by SAM continues to increase as the model becomes more overparameterized. We further present that sparsity can open up an avenue for effective overparameterization in practice.

Why Do We Need Weight Decay in Modern Deep Learning?

Weight decay is a broadly used technique for training state-of-the-art deep networks, including large language models. Despite its widespread usage, its role remains poorly understood. In this work, we highlight that the role of weight decay in modern deep learning is different from its regularization effect studied in classical learning theory. For overparameterized deep networks, we show how weight decay modifies the optimization dynamics enhancing the ever-present implicit regularization of SGD via the loss stabilization mechanism. In contrast, for underparameterized large language models trained with nearly online SGD, we describe how weight decay balances the bias-variance tradeoff in stochastic optimization leading to lower training loss. Moreover, we show that weight decay also prevents sudden loss divergences for bfloat16 mixed-precision training which is a crucial tool for LLM training. Overall, we present a unifying perspective from ResNets on vision tasks to LLMs: weight decay is never useful as an explicit regularizer but instead changes the training dynamics in a desirable way. Our code is available at https://github.com/tml-epfl/why-weight-decay.

Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings

Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection, medical diagnosis, or recommender systems often do not rely on images or text but instead on tabular data. Adversarial robustness in tabular data poses two serious challenges. First, tabular datasets often contain categorical features, and therefore cannot be tackled directly with existing optimization procedures. Second, in the tabular domain, algorithms that are not based on deep networks are widely used and offer great performance, but algorithms to enhance robustness are tailored to neural networks (e.g. adversarial training). In this paper, we tackle both challenges. We present a method that allows us to train adversarially robust deep networks for tabular data and to transfer this robustness to other classifiers via universal robust embeddings tailored to categorical data. These embeddings, created using a bilevel alternating minimization framework, can be transferred to boosted trees or random forests making them robust without the need for adversarial training while preserving their high accuracy on tabular data. We show that our methods outperform existing techniques within a practical threat model suitable for tabular data.

Sharpness-Aware Minimization Leads to Low-Rank Features

Sharpness-aware minimization (SAM) is a recently proposed method that minimizes the sharpness of the training loss of a neural network. While its generalization improvement is well-known and is the primary motivation, we uncover an additional intriguing effect of SAM: reduction of the feature rank which happens at different layers of a neural network. We show that this low-rank effect occurs very broadly: for different architectures such as fully-connected networks, convolutional networks, vision transformers and for different objectives such as regression, classification, language-image contrastive training. To better understand this phenomenon, we provide a mechanistic understanding of how low-rank features arise in a simple two-layer network. We observe that a significant number of activations gets entirely pruned by SAM which directly contributes to the rank reduction. We confirm this effect theoretically and check that it can also occur in deep networks, although the overall rank reduction mechanism can be more complex, especially for deep networks with pre-activation skip connections and self-attention layers. We make our code available at https://github.com/tml-epfl/sam-low-rank-features.

A modern look at the relationship between sharpness and generalization

Sharpness of minima is a promising quantity that can correlate with generalization in deep networks and, when optimized during training, can improve generalization. However, standard sharpness is not invariant under reparametrizations of neural networks, and, to fix this, reparametrization-invariant sharpness definitions have been proposed, most prominently adaptive sharpness (Kwon et al., 2021). But does it really capture generalization in modern practical settings? We comprehensively explore this question in a detailed study of various definitions of adaptive sharpness in settings ranging from training from scratch on ImageNet and CIFAR-10 to fine-tuning CLIP on ImageNet and BERT on MNLI. We focus mostly on transformers for which little is known in terms of sharpness despite their widespread usage. Overall, we observe that sharpness does not correlate well with generalization but rather with some training parameters like the learning rate that can be positively or negatively correlated with generalization depending on the setup. Interestingly, in multiple cases, we observe a consistent negative correlation of sharpness with out-of-distribution error implying that sharper minima can generalize better. Finally, we illustrate on a simple model that the right sharpness measure is highly data-dependent, and that we do not understand well this aspect for realistic data distributions. The code of our experiments is available at https://github.com/tml-epfl/sharpness-vs-generalization.

SGD with large step sizes learns sparse features

We showcase important features of the dynamics of the Stochastic Gradient Descent (SGD) in the training of neural networks. We present empirical observations that commonly used large step sizes (i) lead the iterates to jump from one side of a valley to the other causing loss stabilization, and (ii) this stabilization induces a hidden stochastic dynamics orthogonal to the bouncing directions that biases it implicitly toward simple predictors. Furthermore, we show empirically that the longer large step sizes keep SGD high in the loss landscape valleys, the better the implicit regularization can operate and find sparse representations. Notably, no explicit regularization is used so that the regularization effect comes solely from the SGD training dynamics influenced by the step size schedule. Therefore, these observations unveil how, through the step size schedules, both gradient and noise drive together the SGD dynamics through the loss landscape of neural networks. We justify these findings theoretically through the study of simple neural network models as well as qualitative arguments inspired from stochastic processes. Finally, this analysis allows to shed a new light on some common practice and observed phenomena when training neural networks. The code of our experiments is available at https://github.com/tml-epfl/sgd-sparse-features.