The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined — such attacks can be achieved by embedding malicious behaviors during training and activated under specific conditions that trigger malicious outputs. Despite the increasing support for multilingual capabilities in open-source and proprietary LLMs, the impact of backdoor attacks on these systems remains largely under-explored. Our research focuses on cross-lingual backdoor attacks against multilingual LLMs, particularly investigating how poisoning the instructiontuning data for one or two languages can affect the outputs for languages whose instructiontuning data were not poisoned. Despite its simplicity, our empirical analysis reveals that our method exhibits remarkable efficacy in models like BLOOM and GPT-4o, with high attack success rates, surpassing 90% in more than 7 out of 12 languages across various scenarios. Our findings also indicate that more powerful models show increased susceptibility to transferable cross-lingual backdoor attacks, which also applies to LLMs predominantly pre-trained on English/Chinese data, such as Llama2, Llama3, Qwen2.5, and Gemma. Moreover, our experiments demonstrate 1) High Transferability: the backdoor mechanism operates successfully in cross lingual response scenarios across 26 languages, achieving an average attack success rate of 99%, and 2) Robustness: the proposed attack remains effective even after defenses are applied. These findings expose critical security vulnerabilities in multilingual LLMs and highlight the urgent need for more robust, targeted defense strategies to address the unique challenges posed by cross-lingual backdoor transfer.

With the growing integration of AI in daily life, ensuring the robustness of systems to inference-time attacks is crucial. Among the approaches for certifying robustness to such adversarial examples, randomized smoothing has emerged as highly promising due to its nature as a wrapper around arbitrary black-box models. Previous work on randomized smoothing in natural language processing has primarily focused on specific subsets of edit distance operations, such as synonym substitution or word insertion, without exploring the certification of all edit operations. In this paper, we adapt Randomized Deletion (Huang et al., 2023) and propose, CERTified Edit Distance defense (CERT-ED) for natural language classification. Through comprehensive experiments, we demonstrate that CERT-ED outperforms the existing Hamming distance method RanMASK (Zeng et al., 2023) in 4 out of 5 datasets in terms of both accuracy and the cardinality of the certificate. By covering various threat models, including 5 direct and 5 transfer attacks, our method improves empirical robustness in 38 out of 50 settings.

While multilingual machine translation (MNMT) systems hold substantial promise, they also have security vulnerabilities. Our research highlights that MNMT systems can be susceptible to a particularly devious style of backdoor attack, whereby an attacker injects poisoned data into a low-resource language pair to cause malicious translations in other languages, including high-resource languages.Our experimental results reveal that injecting less than 0.01% poisoned data into a low-resource language pair can achieve an average 20% attack success rate in attacking high-resource language pairs. This type of attack is of particular concern, given the larger attack surface of languages inherent to low-resource settings. Our aim is to bring attention to these vulnerabilities within MNMT systems with the hope of encouraging the community to address security concerns in machine translation, especially in the context of low-resource languages.

Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model’s behavior in ways engineered by the attacker. One such tactic involves the implantation of backdoors, achieved by poisoning specific training instances with a textual trigger and a target class label. Several strategies have been proposed to mitigate the risks associated with backdoor attacks by identifying and removing suspected poisoned examples. However, we observe that these strategies fail to offer effective protection against several advanced backdoor attacks. To remedy this deficiency, we propose a novel defensive mechanism that first exploits training dynamics to identify poisoned samples with high precision, followed by a label propagation step to improve recall and thus remove the majority of poisoned instances. Compared with recent advanced defense methods, our method considerably reduces the success rates of several backdoor attacks while maintaining high classification accuracy on clean test sets.

Modern NLP models are often trained over large untrusted datasets, raising the potential for a malicious adversary to compromise model behaviour. For instance, backdoors can be implanted through crafting training instances with a specific textual trigger and a target label. This paper posits that backdoor poisoning attacks exhibit a spurious correlation between simple text features and classification labels, and accordingly, proposes methods for mitigating spurious correlation as means of defence. Our empirical study reveals that the malicious triggers are highly correlated to their target labels; therefore such correlations are extremely distinguishable compared to those scores of benign features, and can be used to filter out potentially problematic instances. Compared with several existing defences, our defence method significantly reduces attack success rates across backdoor attacks, and in the case of insertion-based attacks, our method provides a near-perfect defence.

Backdoor attacks are an insidious security threat against machine learning models. Adversaries can manipulate the predictions of compromised models by inserting triggers into the training phase. Various backdoor attacks have been devised which can achieve nearly perfect attack success without affecting model predictions for clean inputs. Means of mitigating such vulnerabilities are underdeveloped, especially in natural language processing. To fill this gap, we introduce IMBERT, which uses either gradients or self-attention scores derived from victim models to self-defend against backdoor attacks at inference time. Our empirical studies demonstrate that IMBERT can effectively identify up to 98.5% of inserted triggers. Thus, it significantly reduces the attack success rate while attaining competitive accuracy on the clean dataset across widespread insertion-based attacks compared to two baselines. Finally, we show that our approach is model-agnostic, and can be easily ported to several pre-trained transformer models.

Neural Machine Translation (NMT) systems exhibit problematic biases, such as stereotypical gender bias in the translation of occupation terms into languages with grammatical gender. In this paper we describe a new source of bias prevalent in NMT systems, relating to translations of sentences containing person names. To correctly translate such sentences, a NMT system needs to determine the gender of the name. We show that leading systems are particularly poor at this task, especially for female given names. This bias is deeper than given name gender: we show that the translation of terms with ambiguous sentiment can also be affected by person names, and the same holds true for proper nouns denoting race. To mitigate these biases we propose a simple but effective data augmentation method based on randomly switching entities during translation, which effectively eliminates the problem without any effect on translation quality.

Neural machine translation (NMT) systems are vulnerable to backdoor attacks, whereby an attacker injects poisoned samples into training such that a trained model produces malicious translations. Nevertheless, there is little research on defending against such backdoor attacks in NMT. In this paper, we first show that backdoor attacks that have been successful in text classification are also effective against machine translation tasks. We then present a novel defence method that exploits a key property of most backdoor attacks: namely the asymmetry between the source and target language sentences, which is used to facilitate malicious text insertions, substitutions and suchlike. Our technique uses word alignment coupled with language model scoring to detect outlier tokens, and thus can find and filter out training instances which may contain backdoors. Experimental results demonstrate that our technique can significantly reduce the success of various attacks by up to 89.0%, while not affecting predictive accuracy.

NLP models are vulnerable to data poisoning attacks. One type of attack can plant a backdoor in a model by injecting poisoned examples in training, causing the victim model to misclassify test instances which include a specific pattern. Although defences exist to counter these attacks, they are specific to an attack type or pattern. In this paper, we propose a generic defence mechanism by making the training process robust to poisoning attacks through gradient shaping methods, based on differentially private training. We show that our method is highly effective in mitigating, or even eliminating, poisoning attacks on text classification, with only a small cost in predictive accuracy.