Model distillation has become essential for creating deployable language models, but their widespread deployment raises concerns about about their resilience to adversarial manipulation. This paper investigates how adversaries can inject subtle biases into teacher models through minimal data poisoning during training, which propagates to a smaller distilled student model and becomes significantly amplified. We identify two propagation modes: Untargeted (affecting multiple tasks) and Targeted (focusing on specific task while maintaining normal behavior elsewhere). With only 25 poisoned samples (0.25% poisoning rate), student models generate biased responses 76.9% of the time in targeted scenarios versus 69.4% in teachers, while untargeted propagation shows 5.7X-29.2X higher adversarial bias rate in students on unseen tasks. We validate across six bias types (targeted advertisement, phishing link, narrative manipulations, insecure coding practices), various distillation methods, and text/code generation modalities. Current defense mechanisms—including perplexity filtering, bias detection systems, and LLM-based autoraters—prove inadequate against these attacks. We propose practical design principles for building effective adversarial bias mitigation strategies to address this threat vector.

Vulnerability of Frontier language models to misuse has prompted the development of safety measures like filters and alignment training seeking to ensure safety through robustness to adversarially crafted prompts. We assert that robustness is fundamentally insufficient for ensuring safety goals due to inferential threats from dual-intent queries, with current defenses and evaluations failing to account for these risks. To quantify these risks, we introduce a new safety evaluation framework based on $\textit{impermissible information leakage}$ of model outputs and demonstrate how our proposed question-decomposition attack can extract dangerous knowledge from a censored LLM more effectively than traditional jailbreaking. Underlying our proposed evaluation method is a novel information-theoretic threat model of $\textit{inferential adversaries}$, distinguished from $\textit{security adversaries}$, such as jailbreaks, in that success involves inferring impermissible knowledge from victim outputs as opposed to forcing explicitly impermissible victim outputs. Through our information-theoretic framework, we show that ensuring safety against inferential adversaries requires defenses which bound impermissible information leakage, and, such defenses inevitably incur safety-utility trade-offs.

Reinforcement learning with human feedback (RLHF) has become the dominant method to align large models to user preferences. Unlike fine-tuning, for which there are many studies regarding training data memorization, it is not clear how memorization is affected by or introduced in the RLHF alignment process. Understanding this relationship is important as real user data may be collected and used to align large models; if user data is memorized during RLHF and later regurgitated, this could raise privacy concerns. In addition to RLHF, other methods such as Direct Preference Optimization (DPO) and $\Psi$PO have gained popularity for learning directly from human preferences, removing the need for optimizing intermediary reward models with reinforcement learning. In this work, we analyze how training data memorization can surface and propagate through each phase of RLHF and direct preference learning. We focus our study on code completion models, as code completion is one of the most popular use cases for large language models. We find that RLHF significantly decreases the chance that data used for reward modeling and reinforcement learning is memorized in comparison to directly fine-tuning on this data, but that examples already memorized during the fine-tuning stage of RLHF, will, in the majority of cases, remain memorized after RLHF. In contrast, we find that aligning by learning directly from human preference data via a special case of $\Psi$PO, Identity Preference Optimization (IPO), increases the likelihood that training data is regurgitated compared to RLHF. Our work suggests that RLHF, as opposed to direct preference learning, is a safer way to mitigate the risk of regurgitating sensitive preference data when aligning large language models. We find our conclusions are robust across multiple code completion datasets, tasks, and model scales.

Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a *vulnerability*, allowing even end users to diverge models away from their intended behavior. We aim to explain the causes for this phenomenon and link it to the concept of "attention sinks", an emergent LLM behavior crucial for fluency, in which the initial token receives disproportionately high attention scores. Our investigation identifies the neural circuit responsible for attention sinks and shows how long repetitions disrupt this circuit. We extend this finding to other nonrepeating sequences that exhibit similar circuit disruptions. To address this, we propose a targeted patch that effectively resolves the issue without negatively impacting the overall performance of the model. This study provides a mechanistic explanation for an LLM vulnerability, demonstrating how interpretability can diagnose and address issues, and offering insights that pave the way for more secure and reliable models.

It is now a common business practice to buy access to large language model (LLM) inference rather than self-host, because of significant upfront hardware infrastructure and energy costs. However, as a buyer, there is no mechanism to verify the authenticity of the advertised service including the serving hardware platform, e.g. that it is actually being served using an NVIDIA H100. Furthermore, there are reports suggesting that model providers may deliver models that differ slightly from the advertised ones, often to make them run on less expensive hardware. That way, a client pays premium for a capable model access on more expensive hardware, yet ends up being served by a (potentially less capable) cheaper model on cheaper hardware. In this paper we introduce ***hardware and software platform inference (HSPI)*** -- a method for identifying the underlying GPU architecture and software stack of a (black-box) machine learning model solely based on its input-output behavior. Our method leverages the inherent differences of various GPU architectures and compilers to distinguish between different GPU types and software stacks. By analyzing the numerical patterns in the model's outputs, we propose a classification framework capable of accurately identifying the GPU used for model inference as well as the underlying software configuration. Our findings demonstrate the feasibility of inferring GPU type from black-box models. We evaluate HSPI against models served on different real hardware and find that in a white-box setting we can distinguish between different GPUs with between 83.9% and 100% accuracy. Even in a black-box setting we are able to achieve results that are up to three times higher than random guess accuracy.

Jamie Hayes, Marika Swanberg, Harsh Chaudhari, Itay Yona, Ilia Shumailov, Milad Nasr, Christopher A. Choquette-Choo, Katherine Lee, A. Feder Cooper. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

"Machine unlearning" is a popular proposed solution for mitigating the existence of content in an AI model that is problematic for legal or moral reasons, including privacy, copyright, safety, and more. For example, unlearning is often invoked as a solution for removing the effects of specific information from a generative-AI model's parameters, e.g., a particular individual's personal data or the inclusion of copyrighted content in the model's training data. Unlearning is also proposed as a way to prevent a model from generating targeted types of information in its outputs, e.g., generations that closely resemble a particular individual's data or reflect the concept of "Spiderman." Both of these goals--the targeted removal of information from a model and the targeted suppression of information from a model's outputs--present various technical and substantive challenges. We provide a framework for ML researchers and policymakers to think rigorously about these challenges, identifying several mismatches between the goals of unlearning and feasible implementations. These mismatches explain why unlearning is not a general-purpose solution for circumscribing generative-AI model behavior in service of broader positive impact.

State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language models (LLMs). As a result, prior research has either relied on weaker attacks that avoid training references (e.g., fine-tuning attacks), or on stronger attacks applied to small models and datasets. However, weaker attacks have been shown to be brittle and insights from strong attacks in simplified settings do not translate to today's LLMs. These challenges prompt an important question: are the limitations observed in prior work due to attack design choices, or are MIAs fundamentally ineffective on LLMs? We address this question by scaling LiRA--one of the strongest MIAs--to GPT-2 architectures ranging from 10M to 1B parameters, training references on over 20B tokens from the C4 dataset. Our results advance the understanding of MIAs on LLMs in four key ways. While (1) strong MIAs can succeed on pre-trained LLMs, (2) their effectiveness, remains limited (e.g., AUC<0.7) in practical settings. (3) Even when strong MIAs achieve better-than-random AUC, aggregate metrics can conceal substantial per-sample MIA decision instability: due to training randomness, many decisions are so unstable that they are statistically indistinguishable from a coin flip. Finally, (4) the relationship between MIA success and related LLM privacy metrics is not as straightforward as prior work has suggested.

While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the network's architecture. This involves injecting common architectural components, such as activation functions and pooling layers, to subtly introduce a model backdoor that persists even after (full re-)training, an impossible task for other backdoor types. Bober-Irlzar etal. [2023] introduced the first architectural backdoor design, specifically showing how to create a backdoor for a checkerboard pattern. Yet, the full scope and implications of architectural backdoors have remained largely unexplored, in part because of the limitations in the original design. Namely, it could not be used to target custom triggers, required human involvement for detector construction, and provided no performance guarantees. In this work we revisit architectural backdoors and demonstrate realistic threats that they pose. First, we improve on the original design and construct an arbitrary trigger detector which can be used to backdoor any architecture with no human supervision. Second, we taxonomise 12 distinct archi-tectural backdoor types, and provide an evaluation of their performance. Next, to gauge the difficulty of detecting such backdoors, we conduct a human study, revealing that ML developers can only identify suspicious components in common model definitions as backdoors in 37% of cases, while they surprisingly preferred backdoored models in 33% of cases. To contextualise these results, we find that language models outperform humans at the detection of backdoors. Finally, we discuss defenses against architectural backdoors, emphasising the need for robust and comprehensive strategies to safeguard the integrity of ML systems.

Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence mechanisms, such as model fine-tuning or output censorship methods have proven to be fallible at ensuring that LLMs do not return semantically impermissible responses. We present fundamental limitations of verifying the semantic properties of LLM outputs and identifying compositional threats, illustrating inherent challenges of current approaches to censoring LLM outputs. Specifically, we demonstrate that semantic censorship can be perceived as an undecidable problem, and semantic properties of LLM outputs can become impossible to verify when the LLM is capable of providing "encrypted" outputs. We further show challenges of censorship can extend beyond just semantic censorship, as attackers can reconstruct impermissible outputs from a collection of permissible ones. Consequently, we call for a re-evaluation of the problem of censorship and its goals, stressing the need for new definitions and approaches to censorship. In addition, we provide an initial attempt toward achieving this goal through syntactic censorship, drawing from a security perspective to design censorship methods that can provide guarantees.

Deep neural networks, costly to train and rich in intellectual property value, are increasingly threatened by model extraction attacks that compromise their confiden- tiality. Previous attacks have succeeded in reverse-engineering model parameters up to a precision of float64 for models trained on random data with at most three hidden layers using cryptanalytical techniques. However, the process was identified to be very time consuming and not feasible for larger and deeper models trained on standard benchmarks. Our study evaluates the feasibility of parameter extraction methods of Carlini et al. [1] further enhanced by Canales-Martínez et al. [2] for models trained on standard benchmarks. We introduce a unified codebase that integrates previous methods and reveal that computational tools can significantly influence performance. We develop further optimisations to the end-to-end attack and improve the efficiency of extracting weight signs by up to 14.8 times com- pared to former methods through the identification of easier and harder to extract neurons. Contrary to prior assumptions, we identify extraction of weights, not extraction of weight signs, as the critical bottleneck. With our improvements, a 16,721 parameter model with 2 hidden layers trained on MNIST is extracted within only 98 minutes compared to at least 150 minutes previously. Finally, addressing methodological deficiencies observed in previous studies, we propose new ways of robust benchmarking for future model extraction attacks.

Machine learning is vulnerable to adversarial manipulation. Previous literature demonstrated that at the training stage attackers can manipulate data [14] and data sampling procedures [29] to control model behaviour. A common attack goal is to plant backdoors i.e. force the victim model to learn to recognise a trigger known only by the adversary. In this paper, we introduce a new class of backdoor attacks that hide inside model architectures i.e. in the inductive bias of the functions used to train. These backdoors are simple to implement, for instance by publishing open-source code for a backdoored model architecture that others will reuse unknowingly. We demonstrate that model architectural backdoors represent a real threat and, unlike other approaches, can survive a complete re-training from scratch. We formalise the main construction principles behind architectural backdoors, such as a connection between the input and the output, and describe some possible protections against them. We evaluate our attacks on computer vision benchmarks of different scales and demonstrate the underlying vulnerability is pervasive in a variety of common training settings.

The inference of Large language models (LLMs) requires immense computation and memory resources.To curtail these costs, quantisation has emerged as a promising solution, but existing LLM quantisation mainly focuses on 8-bit.In this work, we explore the statistical and learning properties of the LLM layer and attribute the bottleneck of LLM quantisation to numerical scaling offsets.To address this, we adapt block quantisations for LLMs, a family of methods that share scaling factors across packed numbers.Block quantisations efficiently reduce the numerical scaling offsets solely from an arithmetic perspective, without additional treatments in the computational path.Our nearly-lossless quantised 6-bit LLMs achieve a 19× higher arithmetic density and 5× memory density than the float32 baseline, surpassing the prior art 8-bit quantisation by 2.5× in arithmetic density and 1.2× in memory density, without requiring any data calibration or re-training.We also share our insights into sub-8-bit LLM quantisation, including the mismatch between activation and weight distributions, optimal fine-tuning strategies, and a lower quantisation granularity inherent in the statistical properties of LLMs.The latter two tricks enable nearly-lossless 4-bit LLMs on downstream tasks.Our code is open-sourced 1 .

In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or other model updates, with a central party (e.g., a company) coordinating the training. Because data never "leaves" personal devices, FL is often presented as privacy-preserving. Yet, recently it was shown that this protection is but a thin facade, as even a passive, honest-but-curious attacker observing gradients can reconstruct data of individual users contributing to the protocol.In this work, we show a novel data reconstruction attack which allows an active and dishonest central party to efficiently extract user data from the received gradients. While prior work on data reconstruction in FL relies on solving computationally expensive optimization problems or on making easily detectable modifications to the shared model’s architecture or parameters, in our attack the central party makes inconspicuous changes to the shared model’s weights before sending them out to the users. We call the modified weights of our attack trap weights.Our active attacker is able to recover user data perfectly, i.e., with zero error, even when this data stems from the same class. Recovery comes with near-zero costs: the attack requires no complex optimization objectives. Instead, our attacker exploits inherent data leakage from model gradients and simply amplifies this effect by maliciously altering the weights of the shared model through the trap weights. These specificities enable our attack to scale to fully-connected and convolutional deep neural networks trained with large mini-batches of data. For example, for the high-dimensional vision dataset ImageNet, we perfectly reconstruct more than 50% of the training data points from mini-batches as large as 100 data points. In textual tasks, such as IMDB sentiment analysis, more than 65% of data points from mini-batches containing 100 data points can be perfectly reconstructed.

Federated learning (FL) is a framework for users to jointly train a machine learning model. FL is promoted as a privacy-enhancing technology (PET) that provides data minimization: data never "leaves" personal devices and users share only model updates with a server (e.g., a company) coordinating the distributed training. While prior work showed that in vanilla FL a malicious server can extract users’ private data from the model updates, in this work we take it further and demonstrate that a malicious server can reconstruct user data even in hardened versions of the protocol. More precisely, we propose an attack against FL protected with distributed differential privacy (DDP) and secure aggregation (SA). Our attack method is based on the introduction of sybil devices that deviate from the protocol to expose individual users’ data for reconstruction by the server. The underlying root cause for the vulnerability to our attack is a power imbalance: the server orchestrates the whole protocol and users are given little guarantees about the selection of other users participating in the protocol. Moving forward, we discuss requirements for privacy guarantees in FL. We conclude that users should only participate in the protocol when they trust the server or they apply local primitives such as local DP, shifting power away from the server. Yet, the latter approaches come at significant overhead in terms of performance degradation of the trained model, making them less likely to be deployed in practice.

Search engines are vulnerable to attacks against indexing and searching via text encoding manipulation. By imperceptibly perturbing text using uncommon encoded representations, adversaries can control results across search engines for specific search queries. We demonstrate that this attack is successful against two major commercial search engines - Google and Bing - and one open source search engine - Elasticsearch. We further demonstrate that this attack is successful against LLM chat search including Bing’s GPT-4 chatbot and Google’s Bard chatbot. We also present a variant of the attack targeting text summarization and plagiarism detection models, two ML tasks closely tied to search. We provide a set of defenses against these techniques and warn that adversaries can leverage these attacks to launch disinformation campaigns against unsuspecting users, motivating the need for search engine maintainers to patch deployed systems.

As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm. In this paper, we investigate the interplay between vulnerabilities of the image scaling procedure and machine learning models in the decision-based black-box setting. We propose a novel sampling strategy to make a black-box attack exploit vulnerabilities in scaling algorithms, scaling defenses, and the final machine learning model in an end-to-end manner. Based on this scaling-aware attack, we reveal that most existing scaling defenses are ineffective under threat from downstream models. Moreover, we empirically observe that standard black-box attacks can significantly improve their performance by exploiting the vulnerable scaling procedure. We further demonstrate this problem on a commercial Image Analysis API with decision-based black-box attacks.

Defending against adversarial examples remains an open problem. A common belief is that randomness at inference increases the cost of finding adversarial inputs. An example of such a defense is to apply a random transformation to inputs prior to feeding them to the model. In this paper, we empirically and theoretically investigate such stochastic pre-processing defenses and demonstrate that they are flawed. First, we show that most stochastic defenses are weaker than previously thought; they lack sufficient randomness to withstand even standard attacks like projected gradient descent. This casts doubt on a long-held assumption that stochastic defenses invalidate attacks designed to evade deterministic defenses and force attackers to integrate the Expectation over Transformation (EOT) concept. Second, we show that stochastic defenses confront a trade-off between adversarial robustness and model invariance; they become less effective as the defended model acquires more invariance to their randomization. Future work will need to decouple these two effects. We also discuss implications and guidance for future research.

When learning from sensitive data, care must be taken to ensure that training algorithms address privacy concerns. The canonical Private Aggregation of Teacher Ensembles, or PATE, computes output labels by aggregating the predictions of a (possibly distributed) collection of teacher models via a voting mechanism. The mechanism adds noise to attain a differential privacy guarantee with respect to the teachers' training data. In this work, we observe that this use of noise, which makes PATE predictions stochastic, enables new forms of leakage of sensitive information. For a given input, our adversary exploits this stochasticity to extract high-fidelity histograms of the votes submitted by the underlying teachers. From these histograms, the adversary can learn sensitive attributes of the input such as race, gender, or age. Although this attack does not directly violate the differential privacy guarantee, it clearly violates privacy norms and expectations, and would not be possible $\textit{at all}$ without the noise inserted to obtain differential privacy. In fact, counter-intuitively, the attack $\textbf{becomes easier as we add more noise}$ to provide stronger differential privacy. We hope this encourages future work to consider privacy holistically rather than treat differential privacy as a panacea.

Network Architecture Search (NAS) methods have recently gathered much attention. They design networks with better performance and use a much shorter search time compared to traditional manual tuning. Despite their efficiency in model deployments, most NAS algorithms target a single task on a fixed hardware system. However, real-life few-shot learning environments often cover a great number of tasks ($T$) and deployments on a wide variety of hardware platforms ($H$). The combinatorial search complexity $T \times H$ creates a fundamental search efficiency challenge if one naively applies existing NAS methods to these scenarios. To overcome this issue, we show, for the first time, how to rapidly adapt model architectures to new tasks in a \emph{many-task many-hardware} few-shot learning setup by integrating Model Agnostic Meta Learning (MAML) into the NAS flow. The proposed NAS method (H-Meta-NAS) is hardware-aware and performs optimisation in the MAML framework. MetaNAS shows a Pareto dominance compared to a variety of NAS and manual baselines in popular few-shot learning benchmarks with various hardware platforms and constraints. In particular, on the 5-way 1-shot Mini-ImageNet classification task, the proposed method outperforms the best manual baseline by a large margin ($5.21\%$ in accuracy) using $60\%$ less computation.

Several years of research have shown that machine-learning systems are vulnerable to adversarial examples, both in theory and in practice. Until now, such attacks have primarily targeted visual models, exploiting the gap between human and machine perception. Although text-based models have also been attacked with adversarial examples, such attacks struggled to preserve semantic meaning and indistinguishability. In this paper, we explore a large class of adversarial examples that can be used to attack text-based models in a black-box setting without making any human-perceptible visual modification to inputs. We use encoding-specific perturbations that are imperceptible to the human eye to manipulate the outputs of a wide range of Natural Language Processing (NLP) systems from neural machine-translation pipelines to web search engines. We find that with a single imperceptible encoding injection – representing one invisible character, homoglyph, reordering, or deletion – an attacker can significantly reduce the performance of vulnerable models, and with three injections most models can be functionally broken. Our attacks work against currently-deployed commercial systems, including those produced by Microsoft and Google, in addition to open source models published by Facebook, IBM, and HuggingFace. This novel series of attacks presents a significant threat to many language processing systems: an attacker can affect systems in a targeted manner without any assumptions about the underlying model. We conclude that text-based NLP systems require careful input sanitization, just like conventional applications, and that given such systems are now being deployed rapidly at scale, the urgent attention of architects and operators is required.

The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While such devices enable us to train large-scale neural networks in datacenters and deploy them on edge devices, their designers' focus so far is on average-case performance. In this work, we introduce a novel threat vector against neural networks whose energy consumption or decision latency are critical. We show how adversaries can exploit carefully-crafted sponge examples, which are inputs designed to maximise energy consumption and latency, to drive machine learning (ML) systems towards their worst-case performance. Sponge examples are, to our knowledge, the first denial-of-service attack against the ML components of such systems. We mount two variants of our sponge attack on a wide range of state-of-the-art neural network models, and find that language models are surprisingly vulnerable. Sponge examples frequently increase both latency and energy consumption of these models by a factor of 30×. Extensive experiments show that our new attack is effective across different hardware platforms (CPU, GPU and an ASIC simulator) on a wide range of different language tasks. On vision tasks, we show that sponge examples can be produced and a latency degradation observed, but the effect is less pronounced. To demonstrate the effectiveness of sponge examples in the real world, we mount an attack against Microsoft Azure's translator and show an increase of response time from 1ms to 6s (6000×). We conclude by proposing a defense strategy: shifting the analysis of energy consumption in hardware from an average-case to a worst-case perspective.

Inpainting is a learned interpolation technique that is based on generative modeling and used to populate masked or missing pieces in an image; it has wide applications in picture editing and retouching. Recently, inpainting started being used for watermark removal, raising concerns. In this paper we study how to manipulate it using our markpainting technique. First, we show how an image owner with access to an inpainting model can augment their image in such a way that any attempt to edit it using that model will add arbitrary visible information. We find that we can target multiple different models simultaneously with our technique. This can be designed to reconstitute a watermark if the editor had been trying to remove it. Second, we show that our markpainting technique is transferable to models that have different architectures or were trained on different datasets, so watermarks created using it are difficult for adversaries to remove. Markpainting is novel and can be used as a manipulation alarm that becomes visible in the event of inpainting. Source code is available at: https://github.com/iliaishacked/markpainting.

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a novel class of training-time attacks that require no changes to the underlying dataset or model architecture, but instead only change the order in which data are supplied to the model. In particular, we find that the attacker can either prevent the model from learning, or poison it to learn behaviours specified by the attacker. Furthermore, we find that even a single adversarially-ordered epoch can be enough to slow down model learning, or even to reset all of the learning progress. Indeed, the attacks presented here are not specific to the model or dataset, but rather target the stochastic nature of modern learning procedures. We extensively evaluate our attacks on computer vision and natural language benchmarks to find that the adversary can disrupt model training and even introduce backdoors.

Trust and reputation play a core role in underground cybercrime markets, where participants are anonymous and there is little legal recourse for dispute arbitration. These underground markets exist in tension between two opposing forces: the drive to hide incriminating information, and the trust and stability benefits that greater openness yields. Revealing information about transactions to mitigate scams also provides valuable data about the market. We analyse the first dataset, of which we are aware, about the transactions created and completed on a well-known and high-traffic underground marketplace, Hack Forums, along with the associated threads and posts made by its users over two recent years, from June 2018 to June 2020. We use statistical modelling approaches to analyse the economic and social characteristics of the market over three eras, especially its performance as an infrastructure for trust. In the Set-up era, we observe the growth of users making only one transaction, as well as 'power-users' who make many transactions. In the Stable era, we observe a wide range of activities (including large-scale transfers of intermediate currencies such as Amazon Giftcards) which declines slowly from an initial peak. Finally, we analyse the effects of the Covid-19 pandemic, concluding that while we see a significant increase in transactins across all categories, this reflects a stimulus of the market, rather than a transformation. New users overcome the 'cold start' problem by engaging in low-level currency exchanges to prove their trustworthiness. We observe currency exchange accounts for most contracts, and Bitcoin and PayPal are the preferred payment methods by trading values and number of contracts involved. The market is becoming more centralised over time around influential users and threads, with significant changes observed during the Set-up and Covid-19 eras.

Progress in the affective computing field has led to the creation of affect-aware games that aim to adapt to the emotions experienced by the players. In this paper we focus on affect recognition in virtual reality (VR) gaming, a problem that to the best of our knowledge has not yet been sufficiently explored. We aim to answer two research questions: (i) Is it possible to reliably capture and recognize the affective state of a person based on EMG sensors placed on their lower arms, while they interact with the virtual environment? and (ii) Is EMG signal from one arm sufficient for detecting affect? We conducted a study in which 8 people were playing a set of VR games with two EMG sensors placed on their arms. We analysed the EMG signals and extracted a number of features to infer the affective states of the players. Our experimental results show that the EMG measures from left and right arms provide sufficient information to detect emotions experienced by a player of a VR game. Our results also show that classifying a DWT-dbl signal with Support Vector Machine (SVM) yields F1=0.91 for predicting low/high arousal and F1=0.85 for predicting positive/negative valence when using just the left-arm EMG signal. To the best of our knowledge, this is the first work that uses EMG data from arm movements as a single source of affective information and addresses affect recognition in VR gaming.