Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining

Backdoor attacks remain significant security threats to generative large language models (LLMs). Since generative LLMs output sequences of high-dimensional token logits instead of low-dimensional classification logits, most existing backdoor defense methods designed for discriminative models like BERT are ineffective for generative LLMs. Inspired by the observed differences in learning behavior between backdoor and clean mapping in the frequency space, we transform gradients of each training sample, directly influencing parameter updates, into the frequency space. Our findings reveal a distinct separation between the gradients of backdoor and clean samples in the frequency space. Based on this phenomenon, we propose Gradient Clustering in the Frequency Space for Backdoor Sample Filtering (GraCeFul), which leverages sample-wise gradients in the frequency space to effectively identify backdoor samples without requiring retraining LLMs. Experimental results show that GraCeFul outperforms baselines significantly. Notably, GraCeFul exhibits remarkable computational efficiency, achieving nearly 100% recall and F1 scores in identifying backdoor samples, reducing the average success rate of various backdoor attacks to 0% with negligible drops in clean accuracy across multiple free-style question answering datasets. Additionally, GraCeFul generalizes to Llama-2 and Vicuna. The codes are publicly available at https://github.com/ZrW00/GraceFul.

NSmark: Null Space Based Black-box Watermarking Defense Framework for Pre-trained Language Models

Pre-trained language models (PLMs) have emerged as critical intellectual property (IP) assets that necessitate protection. Although various watermarking strategies have been proposed, they remain vulnerable to Linear Functionality Equivalence Attacks (LFEA), which can invalidate most existing white-box watermarks without prior knowledge of the watermarking scheme or training data. This paper further analyzes and extends the attack scenarios of LFEA to the commonly employed black-box settings for PLMs by considering Last-Layer outputs (dubbed LL-LFEA). We discover that the null space of the output matrix remains invariant against LL-LFEA attacks. Based on this finding, we propose NSmark, a task-agnostic, black-box watermarking scheme capable of resisting LL-LFEA attacks. NSmark consists of three phases: (i) watermark generation using the digital signature of the owner, enhanced by spread spectrum modulation for increased robustness; (ii) watermark embedding through an output mapping extractor that preserves PLM performance while maximizing watermark capacity; (iii) watermark verification, assessed by extraction rate and null space conformity. Extensive experiments on both pre-training and downstream tasks confirm the effectiveness, reliability, fidelity, and robustness of our approach. Code is available at https://github.com/dongdongzhaoUP/NSmark.

Flooding Spread of Manipulated Knowledge in LLM-Based Multi-Agent Communities

The rapid adoption of large language models (LLMs) in multi-agent systems has highlighted their impressive capabilities in various applications, such as collaborative problem-solving and autonomous negotiation. However, the security implications of these LLM-based multi-agent systems have not been thoroughly investigated, particularly concerning the spread of manipulated knowledge. In this paper, we investigate this critical issue by constructing a detailed threat model and a comprehensive simulation environment that mirrors real-world multi-agent deployments in a trusted platform. Subsequently, we propose a novel two-stage attack method involving Persuasiveness Injection and Manipulated Knowledge Injection to systematically explore the potential for manipulated knowledge (i.e., counterfactual and toxic knowledge) spread without explicit prompt manipulation. Our method leverages the inherent vulnerabilities of LLMs in handling world knowledge, which can be exploited by attackers to unconsciously spread fabricated information. Through extensive experiments, we demonstrate that our attack method can successfully induce LLM-based agents to spread both counterfactual and toxic knowledge without degrading their foundational capabilities during agent communication. Furthermore, we show that these manipulations can persist through popular retrieval-augmented generation frameworks, where several benign agents store and retrieve manipulated chat histories for future interactions. This persistence indicates that even after the interaction has ended, the benign agents may continue to be influenced by manipulated knowledge. Our findings reveal significant security risks in LLM-based multi-agent systems, emphasizing the imperative need for robust defenses against manipulated knowledge spread, such as introducing ``guardian'' agents and advanced fact-checking tools.

TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models

Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages, but the cost and robustness have been criticized. Attacking LLMs is inherently risky in security review, while prohibitively expensive. Besides, the continuous iteration of LLMs will degrade the robustness of backdoors. In this paper, we propose TrojanRAG, which employs a joint backdoor attack in the Retrieval-Augmented Generation, thereby manipulating LLMs in universal attack scenarios. Specifically, the adversary constructs elaborate target contexts and trigger sets. Multiple pairs of backdoor shortcuts are orthogonally optimized by contrastive learning, thus constraining the triggering conditions to a parameter subspace to improve the matching. To improve the recall of the RAG for the target contexts, we introduce a knowledge graph to construct structured data to achieve hard matching at a fine-grained level. Moreover, we normalize the backdoor scenarios in LLMs to analyze the real harm caused by backdoors from both attackers' and users' perspectives and further verify whether the context is a favorable tool for jailbreaking models. Extensive experimental results on truthfulness, language understanding, and harmfulness show that TrojanRAG exhibits versatility threats while maintaining retrieval capabilities on normal queries.

MKF-ADS: Multi-Knowledge Fusion Based Self-supervised Anomaly Detection System for Control Area Network

Control Area Network (CAN) is an essential communication protocol that interacts between Electronic Control Units (ECUs) in the vehicular network. However, CAN is facing stringent security challenges due to innate security risks. Intrusion detection systems (IDSs) are a crucial safety component in remediating Vehicular Electronics and Systems vulnerabilities. However, existing IDSs fail to identify complexity attacks and have higher false alarms owing to capability bottleneck. In this paper, we propose a self-supervised multi-knowledge fused anomaly detection model, called MKF-ADS. Specifically, the method designs an integration framework, including spatial-temporal correlation with an attention mechanism (STcAM) module and patch sparse-transformer module (PatchST). The STcAM with fine-pruning uses one-dimensional convolution (Conv1D) to extract spatial features and subsequently utilizes the Bidirectional Long Short Term Memory (Bi-LSTM) to extract the temporal features, where the attention mechanism will focus on the important time steps. Meanwhile, the PatchST captures the combined contextual features from independent univariate time series. Finally, the proposed method is based on knowledge distillation to STcAM as a student model for learning intrinsic knowledge and cross the ability to mimic PatchST. We conduct extensive experiments on six simulation attack scenarios across various CAN IDs and time steps, and two real attack scenarios, which present a competitive prediction and detection performance. Compared with the baseline in the same paradigm, the error rate and FAR are 2.62\% and 2.41\% and achieve a promising F1-score of 97.3\%.

How Large Language Models Encode Context Knowledge? A Layer-Wise Probing Study

Previous work has showcased the intriguing capability of large language models (LLMs) in retrieving facts and processing context knowledge. However, only limited research exists on the layer-wise capability of LLMs to encode knowledge, which challenges our understanding of their internal mechanisms. In this paper, we devote the first attempt to investigate the layer-wise capability of LLMs through probing tasks. We leverage the powerful generative capability of ChatGPT to construct probing datasets, providing diverse and coherent evidence corresponding to various facts. We employ $\mathcal V$-usable information as the validation metric to better reflect the capability in encoding context knowledge across different layers. Our experiments on conflicting and newly acquired knowledge show that LLMs: (1) prefer to encode more context knowledge in the upper layers; (2) primarily encode context knowledge within knowledge-related entity tokens at lower layers while progressively expanding more knowledge within other tokens at upper layers; and (3) gradually forget the earlier context knowledge retained within the intermediate layers when provided with irrelevant evidence. Code is publicly available at https://github.com/Jometeorie/probing_llama.

Syntactic Ghost: An Imperceptible General-purpose Backdoor Attacks on Pre-trained Language Models

Pre-trained language models (PLMs) have been found susceptible to backdoor attacks, which can transfer vulnerabilities to various downstream tasks. However, existing PLM backdoors are conducted with explicit triggers under the manually aligned, thus failing to satisfy expectation goals simultaneously in terms of effectiveness, stealthiness, and universality. In this paper, we propose a novel approach to achieve invisible and general backdoor implantation, called \textbf{Syntactic Ghost} (synGhost for short). Specifically, the method hostilely manipulates poisoned samples with different predefined syntactic structures as stealth triggers and then implants the backdoor to pre-trained representation space without disturbing the primitive knowledge. The output representations of poisoned samples are distributed as uniformly as possible in the feature space via contrastive learning, forming a wide range of backdoors. Additionally, in light of the unique properties of syntactic triggers, we introduce an auxiliary module to drive the PLMs to learn this knowledge in priority, which can alleviate the interference between different syntactic structures. Experiments show that our method outperforms the previous methods and achieves the predefined objectives. Not only do severe threats to various natural language understanding (NLU) tasks on two tuning paradigms but also to multiple PLMs. Meanwhile, the synGhost is imperceptible against three countermeasures based on perplexity, fine-pruning, and the proposed maxEntropy.

Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning while training the LMs on the poisoned dataset, yet struggles against complex backdoor attacks in real-world scenarios. In this paper, we investigate the learning mechanisms of backdoor LMs in the frequency space by Fourier analysis. Our findings indicate that the backdoor mapping presented on the poisoned datasets exhibits a more discernible inclination towards lower frequency compared to clean mapping, resulting in the faster convergence of backdoor mapping. To alleviate this dilemma, we propose Multi-Scale Low-Rank Adaptation (MuScleLoRA), which deploys multiple radial scalings in the frequency space with low-rank adaptation to the target model and further aligns the gradients when updating parameters. Through downscaling in the frequency space, MuScleLoRA encourages the model to prioritize the learning of relatively high-frequency clean mapping, consequently mitigating backdoor learning. Experimental results demonstrate that MuScleLoRA outperforms baselines significantly. Notably, MuScleLoRA reduces the average success rate of diverse backdoor attacks to below 15\% across multiple datasets and generalizes to various backbone LMs, including BERT, RoBERTa, and Llama2. The codes are available at https://github.com/ZrW00/MuScleLoRA.

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models

Recent work has showcased the powerful capability of large language models (LLMs) in recalling knowledge and reasoning. However, the reliability of LLMs in combining these two capabilities into reasoning through multi-hop facts has not been widely explored. This paper systematically investigates the possibilities for LLMs to utilize shortcuts based on direct connections between the initial and terminal entities of multi-hop knowledge. We first explore the existence of factual shortcuts through Knowledge Neurons, revealing that: (i) the strength of factual shortcuts is highly correlated with the frequency of co-occurrence of initial and terminal entities in the pre-training corpora; (ii) few-shot prompting leverage more shortcuts in answering multi-hop questions compared to chain-of-thought prompting. Then, we analyze the risks posed by factual shortcuts from the perspective of multi-hop knowledge editing. Analysis shows that approximately 20% of the failures are attributed to shortcuts, and the initial and terminal entities in these failure instances usually have higher co-occurrences in the pre-training corpus. Finally, we propose erasing shortcut neurons to mitigate the associated risks and find that this approach significantly reduces failures in multiple-hop knowledge editing caused by shortcuts.

Improving Non-autoregressive Machine Translation with Error Exposure and Consistency Regularization

Being one of the IR-NAT (Iterative-refinemennt-based NAT) frameworks, the Conditional Masked Language Model (CMLM) adopts the mask-predict paradigm to re-predict the masked low-confidence tokens. However, CMLM suffers from the data distribution discrepancy between training and inference, where the observed tokens are generated differently in the two cases. In this paper, we address this problem with the training approaches of error exposure and consistency regularization (EECR). We construct the mixed sequences based on model prediction during training, and propose to optimize over the masked tokens under imperfect observation conditions. We also design a consistency learning method to constrain the data distribution for the masked tokens under different observing situations to narrow down the gap between training and inference. The experiments on five translation benchmarks obtains an average improvement of 0.68 and 0.40 BLEU scores compared to the base models, respectively, and our CMLMC-EECR achieves the best performance with a comparable translation quality with the Transformer. The experiments results demonstrate the effectiveness of our method.