Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP

Vision-Language models like CLIP have been shown to be highly effective at linking visual perception and natural language understanding, enabling sophisticated image-text capabilities, including strong retrieval and zero-shot classification performance. Their widespread use, as well as the fact that CLIP models are trained on image-text pairs from the web, make them both a worthwhile and relatively easy target for backdoor attacks. As training foundational models, such as CLIP, from scratch is very expensive, this paper focuses on cleaning potentially poisoned models via fine-tuning. We first show that existing cleaning techniques are not effective against simple structured triggers used in Blended or BadNet backdoor attacks, exposing a critical vulnerability for potential real-world deployment of these models. Then, we introduce PAR, Perturb and Recover, a surprisingly simple yet effective mechanism to remove backdoors from CLIP models. Through extensive experiments across different encoders and types of backdoor attacks, we show that PAR achieves high backdoor removal rate while preserving good standard performance. Finally, we illustrate that our approach is effective even only with synthetic text-image pairs, i.e. without access to real training data. The code and models are available at \href{https://github.com/nmndeep/PerturbAndRecover}{https://github.com/nmndeep/PerturbAndRecover}.

Is In-Context Learning Sufficient for Instruction Following in LLMs?

In-context learning (ICL) allows LLMs to learn from examples without changing their weights, which is a particularly promising capability for long-context LLMs that can potentially learn from many examples. Recently, Lin et al. (2024) proposed URIAL, a method using only three in-context examples to align base LLMs, achieving non-trivial instruction following performance. In this work, we show that, while effective, ICL alignment with URIAL still underperforms compared to instruction fine-tuning on established benchmarks such as MT-Bench and AlpacaEval 2.0 (LC), especially with more capable base LMs. Unlike for tasks such as classification, translation, or summarization, adding more ICL demonstrations for long-context LLMs does not systematically improve instruction following performance. To address this limitation, we derive a greedy selection approach for ICL examples that noticeably improves performance, yet without bridging the gap to instruction fine-tuning. Finally, we provide a series of ablation studies to better understand the reasons behind the remaining gap, and we show how some aspects of ICL depart from the existing knowledge and are specific to the instruction tuning setting. Overall, our work advances the understanding of ICL as an alignment technique. We provide our code at https://github.com/tml-epfl/icl-alignment.

Competition Report: Finding Universal Jailbreak Backdoors in Aligned LLMs

Large language models are aligned to be safe, preventing users from generating harmful content like misinformation or instructions for illegal activities. However, previous work has shown that the alignment process is vulnerable to poisoning attacks. Adversaries can manipulate the safety training data to inject backdoors that act like a universal sudo command: adding the backdoor string to any prompt enables harmful responses from models that, otherwise, behave safely. Our competition, co-located at IEEE SaTML 2024, challenged participants to find universal backdoors in several large language models. This report summarizes the key findings and promising ideas for future research.

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.

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Multi-modal foundation models like OpenFlamingo, LLaVA, and GPT-4 are increasingly used for various real-world tasks. Prior work has shown that these models are highly vulnerable to adversarial attacks on the vision modality. These attacks can be leveraged to spread fake information or defraud users, and thus pose a significant risk, which makes the robustness of large multi-modal foundation models a pressing problem. The CLIP model, or one of its variants, is used as a frozen vision encoder in many vision-language models (VLMs), e.g. LLaVA and OpenFlamingo. We propose an unsupervised adversarial fine-tuning scheme to obtain a robust CLIP vision encoder, which yields robustness on all vision down-stream tasks (VLMs, zero-shot classification) that rely on CLIP. In particular, we show that stealth-attacks on users of VLMs by a malicious third party providing manipulated images are no longer possible once one replaces the original CLIP model with our robust one. No retraining or fine-tuning of the VLM is required. The code and robust models are available at https://github.com/chs20/RobustVLM

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.

Segment (Almost) Nothing: Prompt-Agnostic Adversarial Attacks on Segmentation Models

General purpose segmentation models are able to generate (semantic) segmentation masks from a variety of prompts, including visual (points, boxed, etc.) and textual (object names) ones. In particular, input images are pre-processed by an image encoder to obtain embedding vectors which are later used for mask predictions. Existing adversarial attacks target the end-to-end tasks, i.e. aim at altering the segmentation mask predicted for a specific image-prompt pair. However, this requires running an individual attack for each new prompt for the same image. We propose instead to generate prompt-agnostic adversarial attacks by maximizing the $\ell_2$-distance, in the latent space, between the embedding of the original and perturbed images. Since the encoding process only depends on the image, distorted image representations will cause perturbations in the segmentation masks for a variety of prompts. We show that even imperceptible $\ell_\infty$-bounded perturbations of radius $\epsilon=1/255$ are often sufficient to drastically modify the masks predicted with point, box and text prompts by recently proposed foundation models for segmentation. Moreover, we explore the possibility of creating universal, i.e. non image-specific, attacks which can be readily applied to any input without further computational cost.

Robust Semantic Segmentation: Strong Adversarial Attacks and Fast Training of Robust Models

While a large amount of work has focused on designing adversarial attacks against image classifiers, only a few methods exist to attack semantic segmentation models. We show that attacking segmentation models presents task-specific challenges, for which we propose novel solutions. Our final evaluation protocol outperforms existing methods, and shows that those can overestimate the robustness of the models. Additionally, so far adversarial training, the most successful way for obtaining robust image classifiers, could not be successfully applied to semantic segmentation. We argue that this is because the task to be learned is more challenging, and requires significantly higher computational effort than for image classification. As a remedy, we show that by taking advantage of recent advances in robust ImageNet classifiers, one can train adversarially robust segmentation models at limited computational cost by fine-tuning robust backbones.

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

While adversarial training has been extensively studied for ResNet architectures and low resolution datasets like CIFAR, much less is known for ImageNet. Given the recent debate about whether transformers are more robust than convnets, we revisit adversarial training on ImageNet comparing ViTs and ConvNeXts. Extensive experiments show that minor changes in architecture, most notably replacing PatchStem with ConvStem, and training scheme have a significant impact on the achieved robustness. These changes not only increase robustness in the seen $\ell_\infty$-threat model, but even more so improve generalization to unseen $\ell_1/\ell_2$-robustness. Our modified ConvNeXt, ConvNeXt + ConvStem, yields the most robust models across different ranges of model parameters and FLOPs.