UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Deep neural networks (DNNs) have demonstrated effectiveness in various fields. However, DNNs are vulnerable to backdoor attacks, which inject a unique pattern, called trigger, into the input to cause misclassification to an attack-chosen target label. While existing works have proposed various methods to mitigate backdoor effects in poisoned models, they tend to be less effective against recent advanced attacks. In this paper, we introduce a novel post-training defense technique UNIT that can effectively eliminate backdoor effects for a variety of attacks. In specific, UNIT approximates a unique and tight activation distribution for each neuron in the model. It then proactively dispels substantially large activation values that exceed the approximated boundaries. Our experimental results demonstrate that UNIT outperforms 7 popular defense methods against 14 existing backdoor attacks, including 2 advanced attacks, using only 5\% of clean training data. UNIT is also cost efficient. The code is accessible at https://github.com/Megum1/UNIT.

Threat Behavior Textual Search by Attention Graph Isomorphism

Cyber attacks cause over \$1 trillion loss every year. An important task for cyber security analysts is attack forensics. It entails understanding malware behaviors and attack origins. However, existing automated or manual malware analysis can only disclose a subset of behaviors due to inherent difficulties (e.g., malware cloaking and obfuscation). As such, analysts often resort to text search techniques to identify existing malware reports based on the symptoms they observe, exploiting the fact that malware samples share a lot of similarity, especially those from the same origin. In this paper, we propose a novel malware behavior search technique that is based on graph isomorphism at the attention layers of Transformer models. We also compose a large dataset collected from various agencies to facilitate such research. Our technique outperforms state-of-the-art methods, such as those based on sentence embeddings and keywords by 6-14%. In the case study of 10 real-world malwares, our technique can correctly attribute 8 of them to their ground truth origins while using Google only works for 3 cases.

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks typically leverage a universal trigger pattern or transformation function, such that the trigger can cause misclassification for any input. In response to this, recent papers have introduced attacks using sample-specific invisible triggers crafted through special transformation functions. While these approaches manage to evade detection to some extent, they reveal vulnerability to existing backdoor mitigation techniques. To address and enhance both evasiveness and resilience, we introduce a novel backdoor attack LOTUS. Specifically, it leverages a secret function to separate samples in the victim class into a set of partitions and applies unique triggers to different partitions. Furthermore, LOTUS incorporates an effective trigger focusing mechanism, ensuring only the trigger corresponding to the partition can induce the backdoor behavior. Extensive experimental results show that LOTUS can achieve high attack success rate across 4 datasets and 7 model structures, and effectively evading 13 backdoor detection and mitigation techniques. The code is available at https://github.com/Megum1/LOTUS.

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia

Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities. As they find increased use in sensitive tasks, safety concerns have gained widespread attention. Extensive efforts have been dedicated to aligning LLMs with human moral principles to ensure their safe deployment. Despite their potential, recent research indicates aligned LLMs are prone to specialized jailbreaking prompts that bypass safety measures to elicit violent and harmful content. The intrinsic discrete nature and substantial scale of contemporary LLMs pose significant challenges in automatically generating diverse, efficient, and potent jailbreaking prompts, representing a continuous obstacle. In this paper, we introduce RIPPLE (Rapid Optimization via Subconscious Exploitation and Echopraxia), a novel optimization-based method inspired by two psychological concepts: subconsciousness and echopraxia, which describe the processes of the mind that occur without conscious awareness and the involuntary mimicry of actions, respectively. Evaluations across 6 open-source LLMs and 4 commercial LLM APIs show RIPPLE achieves an average Attack Success Rate of 91.5\%, outperforming five current methods by up to 47.0\% with an 8x reduction in overhead. Furthermore, it displays significant transferability and stealth, successfully evading established detection mechanisms. The code of our work is available at \url{https://github.com/SolidShen/RIPPLE_official/tree/official}

Make Them Spill the Beans! Coercive Knowledge Extraction from LLMs

Large Language Models (LLMs) are now widely used in various applications, making it crucial to align their ethical standards with human values. However, recent jail-breaking methods demonstrate that this alignment can be undermined using carefully constructed prompts. In our study, we reveal a new threat to LLM alignment when a bad actor has access to the model's output logits, a common feature in both open-source LLMs and many commercial LLM APIs (e.g., certain GPT models). It does not rely on crafting specific prompts. Instead, it exploits the fact that even when an LLM rejects a toxic request, a harmful response often hides deep in the output logits. By forcefully selecting lower-ranked output tokens during the auto-regressive generation process at a few critical output positions, we can compel the model to reveal these hidden responses. We term this process model interrogation. This approach differs from and outperforms jail-breaking methods, achieving 92% effectiveness compared to 62%, and is 10 to 20 times faster. The harmful content uncovered through our method is more relevant, complete, and clear. Additionally, it can complement jail-breaking strategies, with which results in further boosting attack performance. Our findings indicate that interrogation can extract toxic knowledge even from models specifically designed for coding tasks.

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift

Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training. However, they are vulnerable to backdoor attacks as reported by recent studies. When a data input (e.g., some Gaussian noise) is stamped with a trigger (e.g., a white patch), the backdoored model always generates the target image (e.g., an improper photo). However, effective defense strategies to mitigate backdoors from DMs are underexplored. To bridge this gap, we propose the first backdoor detection and removal framework for DMs. We evaluate our framework Elijah on hundreds of DMs of 3 types including DDPM, NCSN and LDM, with 13 samplers against 3 existing backdoor attacks. Extensive experiments show that our approach can have close to 100% detection accuracy and reduce the backdoor effects to close to zero without significantly sacrificing the model utility.

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP

Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes. Current detection mechanisms are limited by their inability to address more covert backdoor strategies, such as style-based attacks. In this work, we propose an innovative test-time poisoned sample detection framework that hinges on the interpretability of model predictions, grounded in the semantic meaning of inputs. We contend that triggers (e.g., infrequent words) are not supposed to fundamentally alter the underlying semantic meanings of poisoned samples as they want to stay stealthy. Based on this observation, we hypothesize that while the model's predictions for paraphrased clean samples should remain stable, predictions for poisoned samples should revert to their true labels upon the mutations applied to triggers during the paraphrasing process. We employ ChatGPT, a state-of-the-art large language model, as our paraphraser and formulate the trigger-removal task as a prompt engineering problem. We adopt fuzzing, a technique commonly used for unearthing software vulnerabilities, to discover optimal paraphrase prompts that can effectively eliminate triggers while concurrently maintaining input semantics. Experiments on 4 types of backdoor attacks, including the subtle style backdoors, and 4 distinct datasets demonstrate that our approach surpasses baseline methods, including STRIP, RAP, and ONION, in precision and recall.

Backdooring Neural Code Search

Reusing off-the-shelf code snippets from online repositories is a common practice, which significantly enhances the productivity of software developers. To find desired code snippets, developers resort to code search engines through natural language queries. Neural code search models are hence behind many such engines. These models are based on deep learning and gain substantial attention due to their impressive performance. However, the security aspect of these models is rarely studied. Particularly, an adversary can inject a backdoor in neural code search models, which return buggy or even vulnerable code with security/privacy issues. This may impact the downstream software (e.g., stock trading systems and autonomous driving) and cause financial loss and/or life-threatening incidents. In this paper, we demonstrate such attacks are feasible and can be quite stealthy. By simply modifying one variable/function name, the attacker can make buggy/vulnerable code rank in the top 11%. Our attack BADCODE features a special trigger generation and injection procedure, making the attack more effective and stealthy. The evaluation is conducted on two neural code search models and the results show our attack outperforms baselines by 60%. Our user study demonstrates that our attack is more stealthy than the baseline by two times based on the F1 score.

Fusion is Not Enough: Single-Modal Attacks to Compromise Fusion Models in Autonomous Driving

Multi-sensor fusion (MSF) is widely adopted for perception in autonomous vehicles (AVs), particularly for the task of 3D object detection with camera and LiDAR sensors. The rationale behind fusion is to capitalize on the strengths of each modality while mitigating their limitations. The exceptional and leading performance of fusion models has been demonstrated by advanced deep neural network (DNN)-based fusion techniques. Fusion models are also perceived as more robust to attacks compared to single-modal ones due to the redundant information in multiple modalities. In this work, we challenge this perspective with single-modal attacks that targets the camera modality, which is considered less significant in fusion but more affordable for attackers. We argue that the weakest link of fusion models depends on their most vulnerable modality, and propose an attack framework that targets advanced camera-LiDAR fusion models with adversarial patches. Our approach employs a two-stage optimization-based strategy that first comprehensively assesses vulnerable image areas under adversarial attacks, and then applies customized attack strategies to different fusion models, generating deployable patches. Evaluations with five state-of-the-art camera-LiDAR fusion models on a real-world dataset show that our attacks successfully compromise all models. Our approach can either reduce the mean average precision (mAP) of detection performance from 0.824 to 0.353 or degrade the detection score of the target object from 0.727 to 0.151 on average, demonstrating the effectiveness and practicality of our proposed attack framework.

Detecting Backdoors in Pre-trained Encoders

Self-supervised learning in computer vision trains on unlabeled data, such as images or (image, text) pairs, to obtain an image encoder that learns high-quality embeddings for input data. Emerging backdoor attacks towards encoders expose crucial vulnerabilities of self-supervised learning, since downstream classifiers (even further trained on clean data) may inherit backdoor behaviors from encoders. Existing backdoor detection methods mainly focus on supervised learning settings and cannot handle pre-trained encoders especially when input labels are not available. In this paper, we propose DECREE, the first backdoor detection approach for pre-trained encoders, requiring neither classifier headers nor input labels. We evaluate DECREE on over 400 encoders trojaned under 3 paradigms. We show the effectiveness of our method on image encoders pre-trained on ImageNet and OpenAI's CLIP 400 million image-text pairs. Our method consistently has a high detection accuracy even if we have only limited or no access to the pre-training dataset.