Add to Chrome
Add to Firefox
Add to EdgeManli Shu
Coercing LLMs to do and reveal (almost) anything
Feb 21, 2024
It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectrum of adversarial attacks on LLMs is much larger than merely jailbreaking. We provide a broad overview of possible attack surfaces and attack goals. Based on a series of concrete examples, we discuss, categorize and systematize attacks that coerce varied unintended behaviors, such as misdirection, model control, denial-of-service, or data extraction. We analyze these attacks in controlled experiments, and find that many of them stem from the practice of pre-training LLMs with coding capabilities, as well as the continued existence of strange "glitch" tokens in common LLM vocabularies that should be removed for security reasons.
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Feb 05, 2024Vision-Language Models (VLMs) excel in generating textual responses from visual inputs, yet their versatility raises significant security concerns. This study takes the first step in exposing VLMs' susceptibility to data poisoning attacks that can manipulate responses to innocuous, everyday prompts. We introduce Shadowcast, a stealthy data poisoning attack method where poison samples are visually indistinguishable from benign images with matching texts. Shadowcast demonstrates effectiveness in two attack types. The first is Label Attack, tricking VLMs into misidentifying class labels, such as confusing Donald Trump for Joe Biden. The second is Persuasion Attack, which leverages VLMs' text generation capabilities to craft narratives, such as portraying junk food as health food, through persuasive and seemingly rational descriptions. We show that Shadowcast are highly effective in achieving attacker's intentions using as few as 50 poison samples. Moreover, these poison samples remain effective across various prompts and are transferable across different VLM architectures in the black-box setting. This work reveals how poisoned VLMs can generate convincing yet deceptive misinformation and underscores the importance of data quality for responsible deployments of VLMs. Our code is available at: https://github.com/umd-huang-lab/VLM-Poisoning.
Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks
Nov 20, 2023Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural network. However, the recent past has seen the emergence of countless backbones pretrained using various algorithms and datasets. While this abundance of choice has led to performance increases for a range of systems, it is difficult for practitioners to make informed decisions about which backbone to choose. Battle of the Backbones (BoB) makes this choice easier by benchmarking a diverse suite of pretrained models, including vision-language models, those trained via self-supervised learning, and the Stable Diffusion backbone, across a diverse set of computer vision tasks ranging from classification to object detection to OOD generalization and more. Furthermore, BoB sheds light on promising directions for the research community to advance computer vision by illuminating strengths and weakness of existing approaches through a comprehensive analysis conducted on more than 1500 training runs. While vision transformers (ViTs) and self-supervised learning (SSL) are increasingly popular, we find that convolutional neural networks pretrained in a supervised fashion on large training sets still perform best on most tasks among the models we consider. Moreover, in apples-to-apples comparisons on the same architectures and similarly sized pretraining datasets, we find that SSL backbones are highly competitive, indicating that future works should perform SSL pretraining with advanced architectures and larger pretraining datasets. We release the raw results of our experiments along with code that allows researchers to put their own backbones through the gauntlet here: https://github.com/hsouri/Battle-of-the-Backbones
On the Reliability of Watermarks for Large Language Models
Jun 30, 2023
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the detection and documentation of LLM-generated text. Yet a crucial question remains: How reliable is watermarking in realistic settings in the wild? There, watermarked text may be modified to suit a user's needs, or entirely rewritten to avoid detection. We study the robustness of watermarked text after it is re-written by humans, paraphrased by a non-watermarked LLM, or mixed into a longer hand-written document. We find that watermarks remain detectable even after human and machine paraphrasing. While these attacks dilute the strength of the watermark, paraphrases are statistically likely to leak n-grams or even longer fragments of the original text, resulting in high-confidence detections when enough tokens are observed. For example, after strong human paraphrasing the watermark is detectable after observing 800 tokens on average, when setting a 1e-5 false positive rate. We also consider a range of new detection schemes that are sensitive to short spans of watermarked text embedded inside a large document, and we compare the robustness of watermarking to other kinds of detectors.
Bring Your Own Data! Self-Supervised Evaluation for Large Language Models
Jun 29, 2023
With the rise of Large Language Models (LLMs) and their ubiquitous deployment in diverse domains, measuring language model behavior on realistic data is imperative. For example, a company deploying a client-facing chatbot must ensure that the model will not respond to client requests with profanity. Current evaluations approach this problem using small, domain-specific datasets with human-curated labels. These evaluation sets are often sampled from a narrow and simplified distribution, and data sources can unknowingly be leaked into the training set which can lead to misleading evaluations. To bypass these drawbacks, we propose a framework for self-supervised evaluation of LLMs by analyzing their sensitivity or invariance to transformations on the input text. Self-supervised evaluation can directly monitor LLM behavior on datasets collected in the wild or streamed during live model deployment. We demonstrate self-supervised evaluation strategies for measuring closed-book knowledge, toxicity, and long-range context dependence, in addition to sensitivity to grammatical structure and tokenization errors. When comparisons to similar human-labeled benchmarks are available, we find strong correlations between self-supervised and human-supervised evaluations. The self-supervised paradigm complements current evaluation strategies that rely on labeled data.
On the Exploitability of Instruction Tuning
Jun 28, 2023
Instruction tuning is an effective technique to align large language models (LLMs) with human intents. In this work, we investigate how an adversary can exploit instruction tuning by injecting specific instruction-following examples into the training data that intentionally changes the model's behavior. For example, an adversary can achieve content injection by injecting training examples that mention target content and eliciting such behavior from downstream models. To achieve this goal, we propose \textit{AutoPoison}, an automated data poisoning pipeline. It naturally and coherently incorporates versatile attack goals into poisoned data with the help of an oracle LLM. We showcase two example attacks: content injection and over-refusal attacks, each aiming to induce a specific exploitable behavior. We quantify and benchmark the strength and the stealthiness of our data poisoning scheme. Our results show that AutoPoison allows an adversary to change a model's behavior by poisoning only a small fraction of data while maintaining a high level of stealthiness in the poisoned examples. We hope our work sheds light on how data quality affects the behavior of instruction-tuned models and raises awareness of the importance of data quality for responsible deployments of LLMs. Code is available at \url{https://github.com/azshue/AutoPoison}.
Model-Agnostic Hierarchical Attention for 3D Object Detection
Jan 06, 2023
Transformers as versatile network architectures have recently seen great success in 3D point cloud object detection. However, the lack of hierarchy in a plain transformer makes it difficult to learn features at different scales and restrains its ability to extract localized features. Such limitation makes them have imbalanced performance on objects of different sizes, with inferior performance on smaller ones. In this work, we propose two novel attention mechanisms as modularized hierarchical designs for transformer-based 3D detectors. To enable feature learning at different scales, we propose Simple Multi-Scale Attention that builds multi-scale tokens from a single-scale input feature. For localized feature aggregation, we propose Size-Adaptive Local Attention with adaptive attention ranges for every bounding box proposal. Both of our attention modules are model-agnostic network layers that can be plugged into existing point cloud transformers for end-to-end training. We evaluate our method on two widely used indoor 3D point cloud object detection benchmarks. By plugging our proposed modules into the state-of-the-art transformer-based 3D detector, we improve the previous best results on both benchmarks, with the largest improvement margin on small objects.
What do Vision Transformers Learn? A Visual Exploration
Dec 13, 2022
Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing studies visually analyze the mechanisms of convolutional neural networks, an analogous exploration of ViTs remains challenging. In this paper, we first address the obstacles to performing visualizations on ViTs. Assisted by these solutions, we observe that neurons in ViTs trained with language model supervision (e.g., CLIP) are activated by semantic concepts rather than visual features. We also explore the underlying differences between ViTs and CNNs, and we find that transformers detect image background features, just like their convolutional counterparts, but their predictions depend far less on high-frequency information. On the other hand, both architecture types behave similarly in the way features progress from abstract patterns in early layers to concrete objects in late layers. In addition, we show that ViTs maintain spatial information in all layers except the final layer. In contrast to previous works, we show that the last layer most likely discards the spatial information and behaves as a learned global pooling operation. Finally, we conduct large-scale visualizations on a wide range of ViT variants, including DeiT, CoaT, ConViT, PiT, Swin, and Twin, to validate the effectiveness of our method.
Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models
Sep 15, 2022
Pre-trained vision-language models (e.g., CLIP) have shown promising zero-shot generalization in many downstream tasks with properly designed text prompts. Instead of relying on hand-engineered prompts, recent works learn prompts using the training data from downstream tasks. While effective, training on domain-specific data reduces a model's generalization capability to unseen new domains. In this work, we propose test-time prompt tuning (TPT), a method that can learn adaptive prompts on the fly with a single test sample. For image classification, TPT optimizes the prompt by minimizing the entropy with confidence selection so that the model has consistent predictions across different augmented views of each test sample. In evaluating generalization to natural distribution shifts, TPT improves the zero-shot top-1 accuracy of CLIP by 3.6% on average, surpassing previous prompt tuning approaches that require additional task-specific training data. In evaluating cross-dataset generalization with unseen categories, TPT performs on par with the state-of-the-art approaches that use additional training data. Project page: https://azshue.github.io/TPT.
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
Aug 03, 2021
Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are responsible for erroneous decisions. We find that samples which cause similar parameters to malfunction are semantically similar. We also show that pruning the most salient parameters for a wrongly classified sample often improves model behavior. Furthermore, fine-tuning a small number of the most salient parameters on a single sample results in error correction on other samples that are misclassified for similar reasons. Based on our parameter saliency method, we also introduce an input-space saliency technique that reveals how image features cause specific network components to malfunction. Further, we rigorously validate the meaningfulness of our saliency maps on both the dataset and case-study levels.