Fairness Feedback Loops: Training on Synthetic Data Amplifies Bias

Model-induced distribution shifts (MIDS) occur as previous model outputs pollute new model training sets over generations of models. This is known as model collapse in the case of generative models, and performative prediction or unfairness feedback loops for supervised models. When a model induces a distribution shift, it also encodes its mistakes, biases, and unfairnesses into the ground truth of its data ecosystem. We introduce a framework that allows us to track multiple MIDS over many generations, finding that they can lead to loss in performance, fairness, and minoritized group representation, even in initially unbiased datasets. Despite these negative consequences, we identify how models might be used for positive, intentional, interventions in their data ecosystems, providing redress for historical discrimination through a framework called algorithmic reparation (AR). We simulate AR interventions by curating representative training batches for stochastic gradient descent to demonstrate how AR can improve upon the unfairnesses of models and data ecosystems subject to other MIDS. Our work takes an important step towards identifying, mitigating, and taking accountability for the unfair feedback loops enabled by the idea that ML systems are inherently neutral and objective.

Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy

The high cost of model training makes it increasingly desirable to develop techniques for unlearning. These techniques seek to remove the influence of a training example without having to retrain the model from scratch. Intuitively, once a model has unlearned, an adversary that interacts with the model should no longer be able to tell whether the unlearned example was included in the model's training set or not. In the privacy literature, this is known as membership inference. In this work, we discuss adaptations of Membership Inference Attacks (MIAs) to the setting of unlearning (leading to their ``U-MIA'' counterparts). We propose a categorization of existing U-MIAs into ``population U-MIAs'', where the same attacker is instantiated for all examples, and ``per-example U-MIAs'', where a dedicated attacker is instantiated for each example. We show that the latter category, wherein the attacker tailors its membership prediction to each example under attack, is significantly stronger. Indeed, our results show that the commonly used U-MIAs in the unlearning literature overestimate the privacy protection afforded by existing unlearning techniques on both vision and language models. Our investigation reveals a large variance in the vulnerability of different examples to per-example U-MIAs. In fact, several unlearning algorithms lead to a reduced vulnerability for some, but not all, examples that we wish to unlearn, at the expense of increasing it for other examples. Notably, we find that the privacy protection for the remaining training examples may worsen as a consequence of unlearning. We also discuss the fundamental difficulty of equally protecting all examples using existing unlearning schemes, due to the different rates at which examples are unlearned. We demonstrate that naive attempts at tailoring unlearning stopping criteria to different examples fail to alleviate these issues.

Architectural Neural Backdoors from First Principles

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 backdoor behavior that persists even after (full re-)training. However, the full scope and implications of architectural backdoors have remained largely unexplored. Bober-Irizar et al. [2023] introduced the first architectural backdoor; they showed how to create a backdoor for a checkerboard pattern, but never explained how to target an arbitrary trigger pattern of choice. In this work we construct an arbitrary trigger detector which can be used to backdoor an architecture with no human supervision. This leads us to revisit the concept of architecture backdoors and taxonomise them, describing 12 distinct types. To gauge the difficulty of detecting such backdoors, we conducted a user 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 contextualize these results, we find that language models outperform humans at the detection of backdoors. Finally, we discuss defenses against architectural backdoors, emphasizing the need for robust and comprehensive strategies to safeguard the integrity of ML systems.

Buffer Overflow in Mixture of Experts

Mixture of Experts (MoE) has become a key ingredient for scaling large foundation models while keeping inference costs steady. We show that expert routing strategies that have cross-batch dependencies are vulnerable to attacks. Malicious queries can be sent to a model and can affect a model's output on other benign queries if they are grouped in the same batch. We demonstrate this via a proof-of-concept attack in a toy experimental setting.

Revisiting Block-based Quantisation: What is Important for Sub-8-bit LLM Inference?

The inference of Large language models (LLMs) requires immense computation and memory resources. To curtail these costs, quantisation has merged 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 $19\times$ higher arithmetic density and $5\times$ memory density than the float32 baseline, surpassing the prior art 8-bit quantisation by $2.5\times$ in arithmetic density and $1.2\times$ 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.

Beyond Labeling Oracles: What does it mean to steal ML models?

Model extraction attacks are designed to steal trained models with only query access, as is often provided through APIs that ML-as-a-Service providers offer. ML models are expensive to train, in part because data is hard to obtain, and a primary incentive for model extraction is to acquire a model while incurring less cost than training from scratch. Literature on model extraction commonly claims or presumes that the attacker is able to save on both data acquisition and labeling costs. We show that the attacker often does not. This is because current attacks implicitly rely on the adversary being able to sample from the victim model's data distribution. We thoroughly evaluate factors influencing the success of model extraction. We discover that prior knowledge of the attacker, i.e. access to in-distribution data, dominates other factors like the attack policy the adversary follows to choose which queries to make to the victim model API. Thus, an adversary looking to develop an equally capable model with a fixed budget has little practical incentive to perform model extraction, since for the attack to work they need to collect in-distribution data, saving only on the cost of labeling. With low labeling costs in the current market, the usefulness of such attacks is questionable. Ultimately, we demonstrate that the effect of prior knowledge needs to be explicitly decoupled from the attack policy. To this end, we propose a benchmark to evaluate attack policy directly.

Human-Producible Adversarial Examples

Visual adversarial examples have so far been restricted to pixel-level image manipulations in the digital world, or have required sophisticated equipment such as 2D or 3D printers to be produced in the physical real world. We present the first ever method of generating human-producible adversarial examples for the real world that requires nothing more complicated than a marker pen. We call them $\textbf{adversarial tags}$. First, building on top of differential rendering, we demonstrate that it is possible to build potent adversarial examples with just lines. We find that by drawing just $4$ lines we can disrupt a YOLO-based model in $54.8\%$ of cases; increasing this to $9$ lines disrupts $81.8\%$ of the cases tested. Next, we devise an improved method for line placement to be invariant to human drawing error. We evaluate our system thoroughly in both digital and analogue worlds and demonstrate that our tags can be applied by untrained humans. We demonstrate the effectiveness of our method for producing real-world adversarial examples by conducting a user study where participants were asked to draw over printed images using digital equivalents as guides. We further evaluate the effectiveness of both targeted and untargeted attacks, and discuss various trade-offs and method limitations, as well as the practical and ethical implications of our work. The source code will be released publicly.

SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks

Machine Learning (ML) systems are vulnerable to adversarial examples, particularly those from query-based black-box attacks. Despite various efforts to detect and prevent such attacks, there is a need for a more comprehensive approach to logging, analyzing, and sharing evidence of attacks. While classic security benefits from well-established forensics and intelligence sharing, Machine Learning is yet to find a way to profile its attackers and share information about them. In response, this paper introduces SEA, a novel ML security system to characterize black-box attacks on ML systems for forensic purposes and to facilitate human-explainable intelligence sharing. SEA leverages the Hidden Markov Models framework to attribute the observed query sequence to known attacks. It thus understands the attack's progression rather than just focusing on the final adversarial examples. Our evaluations reveal that SEA is effective at attack attribution, even on their second occurrence, and is robust to adaptive strategies designed to evade forensics analysis. Interestingly, SEA's explanations of the attack behavior allow us even to fingerprint specific minor implementation bugs in attack libraries. For example, we discover that the SignOPT and Square attacks implementation in ART v1.14 sends over 50% specific zero difference queries. We thoroughly evaluate SEA on a variety of settings and demonstrate that it can recognize the same attack's second occurrence with 90+% Top-1 and 95+% Top-3 accuracy.

LLM Censorship: A Machine Learning Challenge or a Computer Security Problem?

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 using LLMs, have proven to be fallible, as LLMs can still generate problematic responses. Commonly employed censorship approaches treat the issue as a machine learning problem and rely on another LM to detect undesirable content in LLM outputs. In this paper, we present the theoretical limitations of such semantic censorship approaches. Specifically, we demonstrate that semantic censorship can be perceived as an undecidable problem, highlighting the inherent challenges in censorship that arise due to LLMs' programmatic and instruction-following capabilities. Furthermore, we argue that the challenges extend beyond semantic censorship, as knowledgeable attackers can reconstruct impermissible outputs from a collection of permissible ones. As a result, we propose that the problem of censorship needs to be reevaluated; it should be treated as a security problem which warrants the adaptation of security-based approaches to mitigate potential risks.