Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots

Chatbots are used in many applications, e.g., automated agents, smart home assistants, interactive characters in online games, etc. Therefore, it is crucial to ensure they do not behave in undesired manners, providing offensive or toxic responses to users. This is not a trivial task as state-of-the-art chatbot models are trained on large, public datasets openly collected from the Internet. This paper presents a first-of-its-kind, large-scale measurement of toxicity in chatbots. We show that publicly available chatbots are prone to providing toxic responses when fed toxic queries. Even more worryingly, some non-toxic queries can trigger toxic responses too. We then set out to design and experiment with an attack, ToxicBuddy, which relies on fine-tuning GPT-2 to generate non-toxic queries that make chatbots respond in a toxic manner. Our extensive experimental evaluation demonstrates that our attack is effective against public chatbot models and outperforms manually-crafted malicious queries proposed by previous work. We also evaluate three defense mechanisms against ToxicBuddy, showing that they either reduce the attack performance at the cost of affecting the chatbot's utility or are only effective at mitigating a portion of the attack. This highlights the need for more research from the computer security and online safety communities to ensure that chatbot models do not hurt their users. Overall, we are confident that ToxicBuddy can be used as an auditing tool and that our work will pave the way toward designing more effective defenses for chatbot safety.

Cerberus: Exploring Federated Prediction of Security Events

Modern defenses against cyberattacks increasingly rely on proactive approaches, e.g., to predict the adversary's next actions based on past events. Building accurate prediction models requires knowledge from many organizations; alas, this entails disclosing sensitive information, such as network structures, security postures, and policies, which might often be undesirable or outright impossible. In this paper, we explore the feasibility of using Federated Learning (FL) to predict future security events. To this end, we introduce Cerberus, a system enabling collaborative training of Recurrent Neural Network (RNN) models for participating organizations. The intuition is that FL could potentially offer a middle-ground between the non-private approach where the training data is pooled at a central server and the low-utility alternative of only training local models. We instantiate Cerberus on a dataset obtained from a major security company's intrusion prevention product and evaluate it vis-a-vis utility, robustness, and privacy, as well as how participants contribute to and benefit from the system. Overall, our work sheds light on both the positive aspects and the challenges of using FL for this task and paves the way for deploying federated approaches to predictive security.

Finding MNEMON: Reviving Memories of Node Embeddings

Previous security research efforts orbiting around graphs have been exclusively focusing on either (de-)anonymizing the graphs or understanding the security and privacy issues of graph neural networks. Little attention has been paid to understand the privacy risks of integrating the output from graph embedding models (e.g., node embeddings) with complex downstream machine learning pipelines. In this paper, we fill this gap and propose a novel model-agnostic graph recovery attack that exploits the implicit graph structural information preserved in the embeddings of graph nodes. We show that an adversary can recover edges with decent accuracy by only gaining access to the node embedding matrix of the original graph without interactions with the node embedding models. We demonstrate the effectiveness and applicability of our graph recovery attack through extensive experiments.

Feels Bad Man: Dissecting Automated Hateful Meme Detection Through the Lens of Facebook's Challenge

Internet memes have become a dominant method of communication; at the same time, however, they are also increasingly being used to advocate extremism and foster derogatory beliefs. Nonetheless, we do not have a firm understanding as to which perceptual aspects of memes cause this phenomenon. In this work, we assess the efficacy of current state-of-the-art multimodal machine learning models toward hateful meme detection, and in particular with respect to their generalizability across platforms. We use two benchmark datasets comprising 12,140 and 10,567 images from 4chan's "Politically Incorrect" board (/pol/) and Facebook's Hateful Memes Challenge dataset to train the competition's top-ranking machine learning models for the discovery of the most prominent features that distinguish viral hateful memes from benign ones. We conduct three experiments to determine the importance of multimodality on classification performance, the influential capacity of fringe Web communities on mainstream social platforms and vice versa, and the models' learning transferability on 4chan memes. Our experiments show that memes' image characteristics provide a greater wealth of information than its textual content. We also find that current systems developed for online detection of hate speech in memes necessitate further concentration on its visual elements to improve their interpretation of underlying cultural connotations, implying that multimodal models fail to adequately grasp the intricacies of hate speech in memes and generalize across social media platforms.

Slapping Cats, Bopping Heads, and Oreo Shakes: Understanding Indicators of Virality in TikTok Short Videos

Short videos have become one of the leading media used by younger generations to express themselves online and thus a driving force in shaping online culture. In this context, TikTok has emerged as a platform where viral videos are often posted first. In this paper, we study what elements of short videos posted on TikTok contribute to their virality. We apply a mixed-method approach to develop a codebook and identify important virality features. We do so vis-\`a-vis three research hypotheses; namely, that: 1) the video content, 2) TikTok's recommendation algorithm, and 3) the popularity of the video creator contribute to virality. We collect and label a dataset of 400 TikTok videos and train classifiers to help us identify the features that influence virality the most. While the number of followers is the most powerful predictor, close-up and medium-shot scales also play an essential role. So does the lifespan of the video, the presence of text, and the point of view. Our research highlights the characteristics that distinguish viral from non-viral TikTok videos, laying the groundwork for developing additional approaches to create more engaging online content and proactively identify possibly risky content that is likely to reach a large audience.

ATTACK2VEC: Leveraging Temporal Word Embeddings to Understand the Evolution of Cyberattacks

Despite the fact that cyberattacks are constantly growing in complexity, the research community still lacks effective tools to easily monitor and understand them. In particular, there is a need for techniques that are able to not only track how prominently certain malicious actions, such as the exploitation of specific vulnerabilities, are exploited in the wild, but also (and more importantly) how these malicious actions factor in as attack steps in more complex cyberattacks. In this paper we present ATTACK2VEC, a system that uses temporal word embeddings to model how attack steps are exploited in the wild, and track how they evolve. We test ATTACK2VEC on a dataset of billions of security events collected from the customers of a commercial Intrusion Prevention System over a period of two years, and show that our approach is effective in monitoring the emergence of new attack strategies in the wild and in flagging which attack steps are often used together by attackers (e.g., vulnerabilities that are frequently exploited together). ATTACK2VEC provides a useful tool for researchers and practitioners to better understand cyberattacks and their evolution, and use this knowledge to improve situational awareness and develop proactive defenses.

Tiresias: Predicting Security Events Through Deep Learning

With the increased complexity of modern computer attacks, there is a need for defenders not only to detect malicious activity as it happens, but also to predict the specific steps that will be taken by an adversary when performing an attack. However this is still an open research problem, and previous research in predicting malicious events only looked at binary outcomes (e.g., whether an attack would happen or not), but not at the specific steps that an attacker would undertake. To fill this gap we present Tiresias, a system that leverages Recurrent Neural Networks (RNNs) to predict future events on a machine, based on previous observations. We test Tiresias on a dataset of 3.4 billion security events collected from a commercial intrusion prevention system, and show that our approach is effective in predicting the next event that will occur on a machine with a precision of up to 0.93. We also show that the models learned by Tiresias are reasonably stable over time, and provide a mechanism that can identify sudden drops in precision and trigger a retraining of the system. Finally, we show that the long-term memory typical of RNNs is key in performing event prediction, rendering simpler methods not up to the task.

You are your Metadata: Identification and Obfuscation of Social Media Users using Metadata Information

Metadata are associated to most of the information we produce in our daily interactions and communication in the digital world. Yet, surprisingly, metadata are often still catergorized as non-sensitive. Indeed, in the past, researchers and practitioners have mainly focused on the problem of the identification of a user from the content of a message. In this paper, we use Twitter as a case study to quantify the uniqueness of the association between metadata and user identity and to understand the effectiveness of potential obfuscation strategies. More specifically, we analyze atomic fields in the metadata and systematically combine them in an effort to classify new tweets as belonging to an account using different machine learning algorithms of increasing complexity. We demonstrate that through the application of a supervised learning algorithm, we are able to identify any user in a group of 10,000 with approximately 96.7% accuracy. Moreover, if we broaden the scope of our search and consider the 10 most likely candidates we increase the accuracy of the model to 99.22%. We also found that data obfuscation is hard and ineffective for this type of data: even after perturbing 60% of the training data, it is still possible to classify users with an accuracy higher than 95%. These results have strong implications in terms of the design of metadata obfuscation strategies, for example for data set release, not only for Twitter, but, more generally, for most social media platforms.

MaMaDroid: Detecting Android Malware by Building Markov Chains of Behavioral Models (Extended Version)

As Android becomes increasingly popular, so does malware targeting it, this motivating the research community to propose many different detection techniques. However, the constant evolution of the Android ecosystem, and of malware itself, makes it hard to design robust tools that can operate for long periods of time without the need for modifications or costly re-training. Aiming to address this issue, we set to detect malware from a behavioral point of view, modeled as the sequence of abstracted API calls. We introduce MaMaDroid, a static-analysis based system that abstracts app's API calls to their class, package, or family, and builds a model from their sequences obtained from the call graph of an app as Markov chains. This ensures that the model is more resilient to API changes and the features set is of manageable size. We evaluate MaMaDroid using a dataset of 8.5K benign and 35.5K malicious apps collected over a period of six years, showing that it effectively detects malware (with up to 0.99 F-measure) and keeps its detection capabilities for long periods of time (up to 0.87 F-measure two years after training). We also show that MaMaDroid remarkably improves over DroidAPIMiner, a state-of-the-art detection system that relies on the frequency of (raw) API calls. Aiming to assess whether MaMaDroid's effectiveness mainly stems from the API abstraction or from the sequencing modeling, we also evaluate a variant of it that uses frequency (instead of sequences), of abstracted API calls. We find that it is not as accurate, failing to capture maliciousness when trained on malware samples including API calls that are equally or more frequently used by benign apps.