One of the new developments in chit-chat bots is a long-term memory mechanism that remembers information from past conversations for increasing engagement and consistency of responses. The bot is designed to extract knowledge of personal nature from their conversation partner, e.g., stating preference for a particular color. In this paper, we show that this memory mechanism can result in unintended behavior. In particular, we found that one can combine a personal statement with an informative statement that would lead the bot to remember the informative statement alongside personal knowledge in its long term memory. This means that the bot can be tricked into remembering misinformation which it would regurgitate as statements of fact when recalling information relevant to the topic of conversation. We demonstrate this vulnerability on the BlenderBot 2 framework implemented on the ParlAI platform and provide examples on the more recent and significantly larger BlenderBot 3 model. We generate 150 examples of misinformation, of which 114 (76%) were remembered by BlenderBot 2 when combined with a personal statement. We further assessed the risk of this misinformation being recalled after intervening innocuous conversation and in response to multiple questions relevant to the injected memory. Our evaluation was performed on both the memory-only and the combination of memory and internet search modes of BlenderBot 2. From the combinations of these variables, we generated 12,890 conversations and analyzed recalled misinformation in the responses. We found that when the chat bot is questioned on the misinformation topic, it was 328% more likely to respond with the misinformation as fact when the misinformation was in the long-term memory.
Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient. However, such systems are also at constant risk of being attacked. While the majority of attacks targeting AI-based applications aim to manipulate classifiers or training data and alter the output of an AI model, recently proposed Sponge Attacks against AI models aim to impede the classifier's execution by consuming substantial resources. In this work, we propose \textit{Dual Denial of Decision (DDoD) attacks against collaborative Human-AI teams}. We discuss how such attacks aim to deplete \textit{both computational and human} resources, and significantly impair decision-making capabilities. We describe DDoD on human and computational resources and present potential risk scenarios in a series of exemplary domains.
Named entity recognition models (NER), are widely used for identifying named entities (e.g., individuals, locations, and other information) in text documents. Machine learning based NER models are increasingly being applied in privacy-sensitive applications that need automatic and scalable identification of sensitive information to redact text for data sharing. In this paper, we study the setting when NER models are available as a black-box service for identifying sensitive information in user documents and show that these models are vulnerable to membership inference on their training datasets. With updated pre-trained NER models from spaCy, we demonstrate two distinct membership attacks on these models. Our first attack capitalizes on unintended memorization in the NER's underlying neural network, a phenomenon NNs are known to be vulnerable to. Our second attack leverages a timing side-channel to target NER models that maintain vocabularies constructed from the training data. We show that different functional paths of words within the training dataset in contrast to words not previously seen have measurable differences in execution time. Revealing membership status of training samples has clear privacy implications, e.g., in text redaction, sensitive words or phrases to be found and removed, are at risk of being detected in the training dataset. Our experimental evaluation includes the redaction of both password and health data, presenting both security risks and privacy/regulatory issues. This is exacerbated by results that show memorization with only a single phrase. We achieved 70% AUC in our first attack on a text redaction use-case. We also show overwhelming success in the timing attack with 99.23% AUC. Finally we discuss potential mitigation approaches to realize the safe use of NER models in light of the privacy and security implications of membership inference attacks.
Federated learning is a distributed learning paradigm which seeks to preserve the privacy of each participating node's data. However, federated learning is vulnerable to attacks, specifically to our interest, model integrity attacks. In this paper, we propose a novel method for malicious node detection called MANDERA. By transferring the original message matrix into a ranking matrix whose column shows the relative rankings of all local nodes along different parameter dimensions, our approach seeks to distinguish the malicious nodes from the benign ones with high efficiency based on key characteristics of the rank domain. We have proved, under mild conditions, that MANDERA is guaranteed to detect all malicious nodes under typical Byzantine attacks with no prior knowledge or history about the participating nodes. The effectiveness of the proposed approach is further confirmed by experiments on two classic datasets, CIFAR-10 and MNIST. Compared to the state-of-art methods in the literature for defending Byzantine attacks, MANDERA is unique in its way to identify the malicious nodes by ranking and its robustness to effectively defense a wide range of attacks.
Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick the model into producing unexpected behaviors. In this paper, we create covert and natural triggers for textual backdoor attacks, \textit{hidden backdoors}, where triggers can fool both modern language models and human inspection. We deploy our hidden backdoors through two state-of-the-art trigger embedding methods. The first approach via homograph replacement, embeds the trigger into deep neural networks through the visual spoofing of lookalike character replacement. The second approach uses subtle differences between text generated by language models and real natural text to produce trigger sentences with correct grammar and high fluency. We demonstrate that the proposed hidden backdoors can be effective across three downstream security-critical NLP tasks, representative of modern human-centric NLP systems, including toxic comment detection, neural machine translation (NMT), and question answering (QA). Our two hidden backdoor attacks can achieve an Attack Success Rate (ASR) of at least $97\%$ with an injection rate of only $3\%$ in toxic comment detection, $95.1\%$ ASR in NMT with less than $0.5\%$ injected data, and finally $91.12\%$ ASR against QA updated with only 27 poisoning data samples on a model previously trained with 92,024 samples (0.029\%). We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.
With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak information about records in the training dataset via membership inference attacks. In this paper, we take a closer look at another inference attack reported in literature, called attribute inference, whereby an attacker tries to infer missing attributes of a partially known record used in the training dataset by accessing the machine learning model as an API. We show that even if a classification model succumbs to membership inference attacks, it is unlikely to be susceptible to attribute inference attacks. We demonstrate that this is because membership inference attacks fail to distinguish a member from a nearby non-member. We call the ability of an attacker to distinguish the two (similar) vectors as strong membership inference. We show that membership inference attacks cannot infer membership in this strong setting, and hence inferring attributes is infeasible. However, under a relaxed notion of attribute inference, called approximate attribute inference, we show that it is possible to infer attributes close to the true attributes. We verify our results on three publicly available datasets, five membership, and three attribute inference attacks reported in literature.
Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their explicit permission for the purpose of training high-precision face recognition models, creating a serious violation of privacy. Recently, a well-known system named Fawkes (published in USENIX Security 2020) claimed this privacy threat can be neutralized by uploading cloaked user images instead of their original images. In this paper, we present Oriole, a system that combines the advantages of data poisoning attacks and evasion attacks, to thwart the protection offered by Fawkes, by training the attacker face recognition model with multi-cloaked images generated by Oriole. Consequently, the face recognition accuracy of the attack model is maintained and the weaknesses of Fawkes are revealed. Experimental results show that our proposed Oriole system is able to effectively interfere with the performance of the Fawkes system to achieve promising attacking results. Our ablation study highlights multiple principal factors that affect the performance of the Oriole system, including the DSSIM perturbation budget, the ratio of leaked clean user images, and the numbers of multi-cloaks for each uncloaked image. We also identify and discuss at length the vulnerabilities of Fawkes. We hope that the new methodology presented in this paper will inform the security community of a need to design more robust privacy-preserving deep learning models.
Intuitively, a backdoor attack against Deep Neural Networks (DNNs) is to inject hidden malicious behaviors into DNNs such that the backdoor model behaves legitimately for benign inputs, yet invokes a predefined malicious behavior when its input contains a malicious trigger. The trigger can take a plethora of forms, including a special object present in the image (e.g., a yellow pad), a shape filled with custom textures (e.g., logos with particular colors) or even image-wide stylizations with special filters (e.g., images altered by Nashville or Gotham filters). These filters can be applied to the original image by replacing or perturbing a set of image pixels.
With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service'' (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the security of the resulting machine learning models has become an increasingly important topic. The security community has demonstrated that without transparency of the data and the resulting model, there exist many potential security risks, with new risks constantly being discovered. In this paper, we focus on one of these security risks -- poisoning attacks. Specifically, we analyze how attackers may interfere with the results of regression learning by poisoning the training datasets. To this end, we analyze and develop a new poisoning attack algorithm. Our attack, termed Nopt, in contrast with previous poisoning attack algorithms, can produce larger errors with the same proportion of poisoning data-points. Furthermore, we also significantly improve the state-of-the-art defense algorithm, termed TRIM, proposed by Jagielsk et al. (IEEE S&P 2018), by incorporating the concept of probability estimation of unpolluted data-points into the algorithm. Our new defense algorithm, termed Proda, demonstrates an increased effectiveness in reducing errors arising from the poisoning dataset. We highlight that the time complexity of TRIM had not been estimated; however, we deduce from their work that TRIM can take exponential time complexity in the worst-case scenario, in excess of Proda's logarithmic time. The performance of both our proposed attack and defense algorithms is extensively evaluated on four real-world datasets of housing prices, loans, health care, and bike sharing services. We hope that our work will inspire future research to develop more robust learning algorithms immune to poisoning attacks.
We assess the security of machine learning based biometric authentication systems against an attacker who submits uniform random inputs, either as feature vectors or raw inputs, in order to find an accepting sample of a target user. The average false positive rate (FPR) of the system, i.e., the rate at which an impostor is incorrectly accepted as the legitimate user, may be interpreted as a measure of the success probability of such an attack. However, we show that the success rate is often higher than the FPR. In particular, for one reconstructed biometric system with an average FPR of 0.03, the success rate was as high as 0.78. This has implications for the security of the system, as an attacker with only the knowledge of the length of the feature space can impersonate the user with less than 2 attempts on average. We provide detailed analysis of why the attack is successful, and validate our results using four different biometric modalities and four different machine learning classifiers. Finally, we propose mitigation techniques that render such attacks ineffective, with little to no effect on the accuracy of the system.