The Double-Edged Sword of Input Perturbations to Robust Accurate Fairness

Deep neural networks (DNNs) are known to be sensitive to adversarial input perturbations, leading to a reduction in either prediction accuracy or individual fairness. To jointly characterize the susceptibility of prediction accuracy and individual fairness to adversarial perturbations, we introduce a novel robustness definition termed robust accurate fairness. Informally, robust accurate fairness requires that predictions for an instance and its similar counterparts consistently align with the ground truth when subjected to input perturbations. We propose an adversarial attack approach dubbed RAFair to expose false or biased adversarial defects in DNN, which either deceive accuracy or compromise individual fairness. Then, we show that such adversarial instances can be effectively addressed by carefully designed benign perturbations, correcting their predictions to be accurate and fair. Our work explores the double-edged sword of input perturbations to robust accurate fairness in DNN and the potential of using benign perturbations to correct adversarial instances.

Whose Side Are You On? Investigating the Political Stance of Large Language Models

Large Language Models (LLMs) have gained significant popularity for their application in various everyday tasks such as text generation, summarization, and information retrieval. As the widespread adoption of LLMs continues to surge, it becomes increasingly crucial to ensure that these models yield responses that are politically impartial, with the aim of preventing information bubbles, upholding fairness in representation, and mitigating confirmation bias. In this paper, we propose a quantitative framework and pipeline designed to systematically investigate the political orientation of LLMs. Our investigation delves into the political alignment of LLMs across a spectrum of eight polarizing topics, spanning from abortion to LGBTQ issues. Across topics, the results indicate that LLMs exhibit a tendency to provide responses that closely align with liberal or left-leaning perspectives rather than conservative or right-leaning ones when user queries include details pertaining to occupation, race, or political affiliation. The findings presented in this study not only reaffirm earlier observations regarding the left-leaning characteristics of LLMs but also surface particular attributes, such as occupation, that are particularly susceptible to such inclinations even when directly steered towards conservatism. As a recommendation to avoid these models providing politicised responses, users should be mindful when crafting queries, and exercise caution in selecting neutral prompt language.

Hufu: A Modality-Agnositc Watermarking System for Pre-Trained Transformers via Permutation Equivariance

With the blossom of deep learning models and services, it has become an imperative concern to safeguard the valuable model parameters from being stolen. Watermarking is considered an important tool for ownership verification. However, current watermarking schemes are customized for different models and tasks, hard to be integrated as an integrated intellectual protection service. We propose Hufu, a modality-agnostic watermarking system for pre-trained Transformer-based models, relying on the permutation equivariance property of Transformers. Hufu embeds watermark by fine-tuning the pre-trained model on a set of data samples specifically permuted, and the embedded model essentially contains two sets of weights -- one for normal use and the other for watermark extraction which is triggered on permuted inputs. The permutation equivariance ensures minimal interference between these two sets of model weights and thus high fidelity on downstream tasks. Since our method only depends on the model itself, it is naturally modality-agnostic, task-independent, and trigger-sample-free. Extensive experiments on the state-of-the-art vision Transformers, BERT, and GPT2 have demonstrated Hufu's superiority in meeting watermarking requirements including effectiveness, efficiency, fidelity, and robustness, showing its great potential to be deployed as a uniform ownership verification service for various Transformers.

Unlearnable Examples For Time Series

Unlearnable examples (UEs) refer to training samples modified to be unlearnable to Deep Neural Networks (DNNs). These examples are usually generated by adding error-minimizing noises that can fool a DNN model into believing that there is nothing (no error) to learn from the data. The concept of UE has been proposed as a countermeasure against unauthorized data exploitation on personal data. While UE has been extensively studied on images, it is unclear how to craft effective UEs for time series data. In this work, we introduce the first UE generation method to protect time series data from unauthorized training by deep learning models. To this end, we propose a new form of error-minimizing noise that can be \emph{selectively} applied to specific segments of time series, rendering them unlearnable to DNN models while remaining imperceptible to human observers. Through extensive experiments on a wide range of time series datasets, we demonstrate that the proposed UE generation method is effective in both classification and generation tasks. It can protect time series data against unauthorized exploitation, while preserving their utility for legitimate usage, thereby contributing to the development of secure and trustworthy machine learning systems.

Multi-Trigger Backdoor Attacks: More Triggers, More Threats

Backdoor attacks have emerged as a primary threat to (pre-)training and deployment of deep neural networks (DNNs). While backdoor attacks have been extensively studied in a body of works, most of them were focused on single-trigger attacks that poison a dataset using a single type of trigger. Arguably, real-world backdoor attacks can be much more complex, e.g., the existence of multiple adversaries for the same dataset if it is of high value. In this work, we investigate the practical threat of backdoor attacks under the setting of \textbf{multi-trigger attacks} where multiple adversaries leverage different types of triggers to poison the same dataset. By proposing and investigating three types of multi-trigger attacks, including parallel, sequential, and hybrid attacks, we provide a set of important understandings of the coexisting, overwriting, and cross-activating effects between different triggers on the same dataset. Moreover, we show that single-trigger attacks tend to cause overly optimistic views of the security of current defense techniques, as all examined defense methods struggle to defend against multi-trigger attacks. Finally, we create a multi-trigger backdoor poisoning dataset to help future evaluation of backdoor attacks and defenses. Although our work is purely empirical, we hope it can help steer backdoor research toward more realistic settings.

LDReg: Local Dimensionality Regularized Self-Supervised Learning

Representations learned via self-supervised learning (SSL) can be susceptible to dimensional collapse, where the learned representation subspace is of extremely low dimensionality and thus fails to represent the full data distribution and modalities. Dimensional collapse also known as the "underfilling" phenomenon is one of the major causes of degraded performance on downstream tasks. Previous work has investigated the dimensional collapse problem of SSL at a global level. In this paper, we demonstrate that representations can span over high dimensional space globally, but collapse locally. To address this, we propose a method called $\textit{local dimensionality regularization (LDReg)}$. Our formulation is based on the derivation of the Fisher-Rao metric to compare and optimize local distance distributions at an asymptotically small radius for each data point. By increasing the local intrinsic dimensionality, we demonstrate through a range of experiments that LDReg improves the representation quality of SSL. The results also show that LDReg can regularize dimensionality at both local and global levels.

End-to-End Anti-Backdoor Learning on Images and Time Series

Backdoor attacks present a substantial security concern for deep learning models, especially those utilized in applications critical to safety and security. These attacks manipulate model behavior by embedding a hidden trigger during the training phase, allowing unauthorized control over the model's output during inference time. Although numerous defenses exist for image classification models, there is a conspicuous absence of defenses tailored for time series data, as well as an end-to-end solution capable of training clean models on poisoned data. To address this gap, this paper builds upon Anti-Backdoor Learning (ABL) and introduces an innovative method, End-to-End Anti-Backdoor Learning (E2ABL), for robust training against backdoor attacks. Unlike the original ABL, which employs a two-stage training procedure, E2ABL accomplishes end-to-end training through an additional classification head linked to the shallow layers of a Deep Neural Network (DNN). This secondary head actively identifies potential backdoor triggers, allowing the model to dynamically cleanse these samples and their corresponding labels during training. Our experiments reveal that E2ABL significantly improves on existing defenses and is effective against a broad range of backdoor attacks in both image and time series domains.

Adversarial Prompt Tuning for Vision-Language Models

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between visual and language modalities. However, these models remain vulnerable to adversarial attacks, particularly in the image modality, presenting considerable security risks. This paper introduces Adversarial Prompt Tuning (AdvPT), a novel technique to enhance the adversarial robustness of image encoders in VLMs. AdvPT innovatively leverages learnable text prompts and aligns them with adversarial image embeddings, to address the vulnerabilities inherent in VLMs without the need for extensive parameter training or modification of the model architecture. We demonstrate that AdvPT improves resistance against white-box and black-box adversarial attacks and exhibits a synergistic effect when combined with existing image-processing-based defense techniques, further boosting defensive capabilities. Comprehensive experimental analyses provide insights into adversarial prompt tuning, a novel paradigm devoted to improving resistance to adversarial images through textual input modifications, paving the way for future robust multimodal learning research. These findings open up new possibilities for enhancing the security of VLMs. Our code will be available upon publication of the paper.

Fake Alignment: Are LLMs Really Aligned Well?

The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety within current research endeavors. This study investigates an interesting issue pertaining to the evaluation of LLMs, namely the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization. That is, the LLM does not have a comprehensive understanding of the complex concept of safety. Instead, it only remembers what to answer for open-ended safety questions, which makes it unable to solve other forms of safety tests. We refer to this phenomenon as fake alignment and construct a comparative benchmark to empirically verify its existence in LLMs. Such fake alignment renders previous evaluation protocols unreliable. To address this, we introduce the Fake alIgNment Evaluation (FINE) framework and two novel metrics--Consistency Score (CS) and Consistent Safety Score (CSS), which jointly assess two complementary forms of evaluation to quantify fake alignment and obtain corrected performance estimates. Applying FINE to 14 widely-used LLMs reveals several models with purported safety are poorly aligned in practice. Our work highlights potential limitations in prevailing alignment methodologies.