Fragile Model Watermark for integrity protection: leveraging boundary volatility and sensitive sample-pairing

Neural networks have increasingly influenced people's lives. Ensuring the faithful deployment of neural networks as designed by their model owners is crucial, as they may be susceptible to various malicious or unintentional modifications, such as backdooring and poisoning attacks. Fragile model watermarks aim to prevent unexpected tampering that could lead DNN models to make incorrect decisions. They ensure the detection of any tampering with the model as sensitively as possible.However, prior watermarking methods suffered from inefficient sample generation and insufficient sensitivity, limiting their practical applicability. Our approach employs a sample-pairing technique, placing the model boundaries between pairs of samples, while simultaneously maximizing logits. This ensures that the model's decision results of sensitive samples change as much as possible and the Top-1 labels easily alter regardless of the direction it moves.

Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics

DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation. Detecting DeepFakes is currently solved with programmed machine learning algorithms. In this work, we investigate the capabilities of multimodal large language models (LLMs) in DeepFake detection. We conducted qualitative and quantitative experiments to demonstrate multimodal LLMs and show that they can expose AI-generated images through careful experimental design and prompt engineering. This is interesting, considering that LLMs are not inherently tailored for media forensic tasks, and the process does not require programming. We discuss the limitations of multimodal LLMs for these tasks and suggest possible improvements.

Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection

Recently, the proliferation of increasingly realistic synthetic images generated by various generative adversarial networks has increased the risk of misuse. Consequently, there is a pressing need to develop a generalizable detector for accurately recognizing fake images. The conventional methods rely on generating diverse training sources or large pretrained models. In this work, we show that, on the contrary, the small and training-free filter is sufficient to capture more general artifact representations. Due to its unbias towards both the training and test sources, we define it as Data-Independent Operator (DIO) to achieve appealing improvements on unseen sources. In our framework, handcrafted filters and the randomly-initialized convolutional layer can be used as the training-free artifact representations extractor with excellent results. With the data-independent operator of a popular classifier, such as Resnet50, one could already reach a new state-of-the-art without bells and whistles. We evaluate the effectiveness of the DIO on 33 generation models, even DALLE and Midjourney. Our detector achieves a remarkable improvement of $13.3\%$, establishing a new state-of-the-art performance. The DIO and its extension can serve as strong baselines for future methods. The code is available at \url{https://github.com/chuangchuangtan/Data-Independent-Operator}.

Invariant Test-Time Adaptation for Vision-Language Model Generalization

Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired datasets. However, these models display significant limitations when applied to long-tail tasks, such as fine-grained image classification, as a result of "decision shortcuts" that hinders their generalization capabilities. In this work, we find that the CLIP model possesses a rich set of features, encompassing both \textit{desired invariant causal features} and \textit{undesired decision shortcuts}. Moreover, the underperformance of CLIP on downstream tasks originates from its inability to effectively utilize pre-trained features in accordance with specific task requirements. To address this challenge, this paper introduces a test-time prompt tuning paradigm that optimizes a learnable prompt, thereby compelling the model to exploit genuine causal invariant features while disregarding decision shortcuts during the inference phase. The proposed method effectively alleviates excessive dependence on potentially misleading, task-irrelevant contextual information, while concurrently emphasizing critical, task-related visual cues. We conduct comparative analysis of the proposed method against various approaches which validates its effectiveness.

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning

As an emerging and vital topic for studying deep neural networks' vulnerability (DNNs), backdoor learning has attracted increasing interest in recent years, and many seminal backdoor attack and defense algorithms are being developed successively or concurrently, in the status of a rapid arms race. However, mainly due to the diverse settings, and the difficulties of implementation and reproducibility of existing works, there is a lack of a unified and standardized benchmark of backdoor learning, causing unfair comparisons, and unreliable conclusions (e.g., misleading, biased or even false conclusions). Consequently, it is difficult to evaluate the current progress and design the future development roadmap of this literature. To alleviate this dilemma, we build a comprehensive benchmark of backdoor learning called BackdoorBench. Our benchmark makes three valuable contributions to the research community. 1) We provide an integrated implementation of state-of-the-art (SOTA) backdoor learning algorithms (currently including 16 attack and 27 defense algorithms), based on an extensible modular-based codebase. 2) We conduct comprehensive evaluations of 12 attacks against 16 defenses, with 5 poisoning ratios, based on 4 models and 4 datasets, thus 11,492 pairs of evaluations in total. 3) Based on above evaluations, we present abundant analysis from 8 perspectives via 18 useful analysis tools, and provide several inspiring insights about backdoor learning. We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning. Finally, we have created a user-friendly website at http://backdoorbench.com, which collects all important information of BackdoorBench, including codebase, docs, leaderboard, and model Zoo.

Enhanced Few-Shot Class-Incremental Learning via Ensemble Models

Few-shot class-incremental learning (FSCIL) aims to continually fit new classes with limited training data, while maintaining the performance of previously learned classes. The main challenges are overfitting the rare new training samples and forgetting old classes. While catastrophic forgetting has been extensively studied, the overfitting problem has attracted less attention in FSCIL. To tackle overfitting challenge, we design a new ensemble model framework cooperated with data augmentation to boost generalization. In this way, the enhanced model works as a library storing abundant features to guarantee fast adaptation to downstream tasks. Specifically, the multi-input multi-output ensemble structure is applied with a spatial-aware data augmentation strategy, aiming at diversifying the feature extractor and alleviating overfitting in incremental sessions. Moreover, self-supervised learning is also integrated to further improve the model generalization. Comprehensive experimental results show that the proposed method can indeed mitigate the overfitting problem in FSCIL, and outperform the state-of-the-art methods.

Defenses in Adversarial Machine Learning: A Survey

Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some particular cases. This phenomenon poses a serious security threat to the practical application of ML systems, and several advanced attack paradigms have been developed to explore it, mainly including backdoor attacks, weight attacks, and adversarial examples. For each individual attack paradigm, various defense paradigms have been developed to improve the model robustness against the corresponding attack paradigm. However, due to the independence and diversity of these defense paradigms, it is difficult to examine the overall robustness of an ML system against different kinds of attacks.This survey aims to build a systematic review of all existing defense paradigms from a unified perspective. Specifically, from the life-cycle perspective, we factorize a complete machine learning system into five stages, including pre-training, training, post-training, deployment, and inference stages, respectively. Then, we present a clear taxonomy to categorize and review representative defense methods at each individual stage. The unified perspective and presented taxonomies not only facilitate the analysis of the mechanism of each defense paradigm but also help us to understand connections and differences among different defense paradigms, which may inspire future research to develop more advanced, comprehensive defenses.

Task-Distributionally Robust Data-Free Meta-Learning

Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. Existing inversion-based DFML methods construct pseudo tasks from a learnable dataset, which is inversely generated from the pre-trained model pool. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift (TDS) and Task-Distribution Corruption (TDC). TDS leads to a biased meta-learner because of the skewed task distribution towards newly generated tasks. TDC occurs when untrusted models characterized by misleading labels or poor quality pollute the task distribution. To tackle these issues, we introduce a robust DFML framework that ensures task distributional robustness. We propose to meta-learn from a pseudo task distribution, diversified through task interpolation within a compact task-memory buffer. This approach reduces the meta-learner's overreliance on newly generated tasks by maintaining consistent performance across a broader range of interpolated memory tasks, thus ensuring its generalization for unseen tasks. Additionally, our framework seamlessly incorporates an automated model selection mechanism into the meta-training phase, parameterizing each model's reliability as a learnable weight. This is optimized with a policy gradient algorithm inspired by reinforcement learning, effectively addressing the non-differentiable challenge posed by model selection. Comprehensive experiments across various datasets demonstrate the framework's effectiveness in mitigating TDS and TDC, underscoring its potential to improve DFML in real-world scenarios.

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Studying backdoor attacks is valuable for model copyright protection and enhancing defenses. While existing backdoor attacks have successfully infected multimodal contrastive learning models such as CLIP, they can be easily countered by specialized backdoor defenses for MCL models. This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses and introduces the \emph{\toolns} attack, which is resistant to backdoor detection and model fine-tuning defenses. To achieve this, we draw motivations from the perspective of the Bayesian rule and propose a dual-embedding guided framework for backdoor attacks. Specifically, we ensure that visual trigger patterns approximate the textual target semantics in the embedding space, making it challenging to detect the subtle parameter variations induced by backdoor learning on such natural trigger patterns. Additionally, we optimize the visual trigger patterns to align the poisoned samples with target vision features in order to hinder the backdoor unlearning through clean fine-tuning. Extensive experiments demonstrate that our attack significantly outperforms state-of-the-art baselines (+45.3% ASR) in the presence of SoTA backdoor defenses, rendering these mitigation and detection strategies virtually ineffective. Furthermore, our approach effectively attacks some more rigorous scenarios like downstream tasks. We believe that this paper raises awareness regarding the potential threats associated with the practical application of multimodal contrastive learning and encourages the development of more robust defense mechanisms.