arXiv subjects

Eleni Triantafillou

Publications and source records attributed to Eleni Triantafillou.

At least 19 recordsLinked to original sources

arXiv2026

Is your algorithm unlearning or untraining?

As models are getting larger and are trained on increasing amounts of data, there has been an explosion of interest into how we can ``delete'' specific data points or behaviours from a trained model, after the fact. This goal has been referred to as ``machine unlearning''. In this note, we argue that the term ``unlearning'' has been overloaded, with different research efforts spanning two distinct problem formulations, but without that distinction having been observed or acknowledged in the literature. This causes various issues, including ambiguity around when an algorithm is expected to work, use of inappropriate metrics and baselines when comparing different algorithms to one another, difficulty in interpreting results, as well as missed opportunities for pursuing critical research directions. In this note, we address this issue by establishing a fundamental distinction between two notions that we identify as \unlearning and \untraining, illustrated in Figure 1. In short, \untraining aims to reverse the effect of having trained on a given forget set, i.e. to remove the influence that that specific forget set examples had on the model during training. On the other hand, the goal of \unlearning is not just to remove the influence of those given examples, but to use those examples for the purpose of more broadly removing the entire underlying distribution from which those examples were sampled (e.g. the concept or behaviour that those examples represent). We discuss technical definitions of these problems and map problem settings studied in the literature to each. We hope to initiate discussions on disambiguating technical definitions and identify a set of overlooked research questions, as we believe that this a key missing step for accelerating progress in the field of ``unlearning''.

cs.LG↗

arXiv2026

Detoxifying LLMs via Representation Erasure-Based Preference Optimization

Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and similar algorithms, reduce the likelihood of harmful continuations, but not robustly so: they are vulnerable to adversarial prompting and easily undone by fine-tuning-based relearning attacks. Indeed, research has shown that these edits to the model are superficial: linear probing reveals that harmful "directions" remain present in representations. To address this, we propose Representation Erasure-based Preference Optimization (REPO), reformulating detoxification as a token-level preference problem. Using a novel objective with preference data, we force the representations of toxic continuations to converge toward their benign counterparts. Our mechanistic analysis reveals that this granular approach is critical: unlike baselines, REPO induces deep, localized edits to toxicity-encoding neurons while preserving general model utility. Exhaustive evaluations show that REPO achieves state-of-the-art robustness, stopping sophisticated threats-including relearning attacks and enhanced GCG jailbreaks-where existing representation- and output-based methods fail.

cs.LG↗

arXiv2026

You Don't Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models

Generative models have been shown to "memorize" certain training data, leading to verbatim or near-verbatim generating images, which may cause privacy concerns or copyright infringement. We introduce Guidance Using Attractive-Repulsive Dynamics (GUARD), a novel framework for memorization mitigation in text-to-image diffusion models. GUARD adjusts the image denoising process to guide the generation away from an original training image and towards one that is distinct from training data while remaining aligned with the prompt, guarding against reproducing training data, without hurting image generation quality. We propose a concrete instantiation of this framework, where the positive target that we steer towards is given by a novel method for (cross) attention attenuation based on (i) a novel statistical mechanism that automatically identifies the prompt positions where cross attention must be attenuated and (ii) attenuating cross-attention in these per-prompt locations. The resulting GUARD offers a surgical, dynamic per-prompt inference-time approach that, we find, is by far the most robust method in terms of consistently producing state-of-the-art results for memorization mitigation across two architectures and for both verbatim and template memorization, while also improving upon or yielding comparable results in terms of image quality.

cs.CV↗

arXiv2026

Step-resolved data attribution for looped transformers

We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for $τ$ recurrent iterations to enable latent reasoning. Existing training-data influence estimators such as TracIn yield a single scalar score that aggregates over all loop iterations, obscuring when during the recurrent computation a training example matters. We introduce \textit{Step-Decomposed Influence (SDI)}, which decomposes TracIn into a length-$τ$ influence trajectory by unrolling the recurrent computation graph and attributing influence to specific loop iterations. To make SDI practical at transformer scale, we propose a TensorSketch implementation that never materialises per-example gradients. Experiments on looped GPT-style models and algorithmic reasoning tasks show that SDI scales excellently, matches full-gradient baselines with low error and supports a broad range of data attribution and interpretability tasks with per-step insights into the latent reasoning process.

cs.LG↗

arXiv2026

Position: Capability Control Should be a Separate Goal From Alignment

Foundation models are trained on broad data distributions, yielding generalist capabilities that enable many downstream applications but also expand the space of potential misuse and failures. This position paper argues that capability control -- imposing restrictions on permissible model behavior -- should be treated as a distinct goal from alignment. While alignment is often context and preference-driven, capability control aims to impose hard operational limits on permissible behaviors, including under adversarial elicitation. We organize capability control mechanisms across the model lifecycle into three layers: (i) data-based control of the training distribution, (ii) learning-based control via weight- or representation-level interventions, and (iii) system-based control via post-deployment guardrails over inputs, outputs, and actions. Because each layer has characteristic failure modes when used in isolation, we advocate for a defense-in-depth approach that composes complementary controls across the full stack. We further outline key open challenges in achieving such control, including the dual-use nature of knowledge and compositional generalization.

cs.LG↗

arXiv2026

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize diverse corrupted data unlearning tasks in vision classifiers. This space is described by two dimensions, the discovery rate (the fraction of the corrupted data that are known at unlearning time) and the statistical regularity of the corrupted data (from random exemplars to shared concepts). Methods proposed previously have been targeted at portions of this space and-we show-fail predictably outside these regions. We propose a novel method, Redirection for Erasing Memory (REM), whose key feature is that corrupted data are redirected to dedicated neurons introduced at unlearning time and then discarded or deactivated to suppress the influence of corrupted data. REM performs strongly across the space of tasks, in contrast to prior SOTA methods that fail outside the regions for which they were designed.

cs.LG↗

arXiv2026

Hair-Trigger Alignment: Black-Box Evaluation Cannot Guarantee Post-Update Alignment

Large Language Models (LLMs) are rarely static and are frequently updated in practice. A growing body of alignment research has shown that models initially deemed ``aligned'' can exhibit misaligned behavior after fine-tuning. These works typically assume that the initial model is aligned based on static black-box evaluation, i.e., the absence of undesired responses to a fixed set of queries. However, the limits of black-box evaluation for post-update scenarios is not explored sufficiently. In this work, we formalize model alignment in both the static and post-update settings and uncover a fundamental limitation of black-box evaluation. We theoretically show that, due to overparameterization, static alignment provides no guarantee of post-update alignment for any update dataset. Moreover, we prove that static black-box probing cannot distinguish a model that is genuinely post-update robust from one that conceals an arbitrary amount of adversarial behavior which can be activated by even a single benign gradient update. We further validate these findings empirically in LLMs across three core alignment domains: privacy, jailbreak safety, and behavioral honesty. We demonstrate the existence of LLMs that pass all standard black-box alignment tests, yet become severely misaligned after a single benign update. Finally, we show that the capacity to hide such latent adversarial behavior increases with model scale, confirming our theoretical prediction that post-update misalignment grows with the number of parameters. Together, our results highlight the inadequacy of static evaluation protocols and emphasize the urgent need for post-update--robust alignment evaluation. Code can be found at: https://github.com/Ybakman/safety_benign_update.

cs.LG↗

arXiv2026

Your Privacy Depends on Others: Collusion Vulnerabilities in Individual Differential Privacy

Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice. We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms: while conforming to the iDP guarantees, an individual's privacy risk is not solely governed by their own privacy budget, but critically depends on the privacy choices of all other data contributors. This creates a mismatch between the promise of individual privacy control and the reality of a system where risk is collectively determined. We demonstrate empirically that certain distributions of privacy preferences can unintentionally inflate the privacy risk of individuals, even when their formal guarantees are met. Moreover, this excess risk provides an exploitable attack vector. A central adversary or a set of colluding adversaries can deliberately choose privacy budgets to amplify vulnerabilities of targeted individuals. Most importantly, this attack operates entirely within the guarantees of DP, hiding this excess vulnerability. Our empirical evaluation demonstrates successful attacks against 62% of targeted individuals, substantially increasing their membership inference susceptibility. To mitigate this, we propose $(\varepsilon_i,δ_i,\overlineΔ)$-iDP a privacy contract that uses $Δ$-divergences to provide users with a hard upper bound on their excess vulnerability, while offering flexibility to mechanism design. Our findings expose a fundamental challenge to the current paradigm, demanding a re-evaluation of how iDP systems are designed, audited, communicated, and deployed to make excess risks transparent and controllable.

cs.CR↗

arXiv2026

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Recent unlearning methods for LLMs are vulnerable to relearning attacks: knowledge believed-to-be-unlearned re-emerges by fine-tuning on a small set of (even seemingly-unrelated) examples. We study this phenomenon in a controlled setting for example-level unlearning in vision classifiers. We make the surprising discovery that forget-set accuracy can recover from around 50% post-unlearning to nearly 100% with fine-tuning on just the retain set -- i.e., zero examples of the forget set. We observe this effect across a wide variety of unlearning methods, whereas for a model retrained from scratch excluding the forget set (gold standard), the accuracy remains at 50%. We observe that resistance to relearning attacks can be predicted by weight-space properties, specifically, $L_2$-distance and linear mode connectivity between the original and the unlearned model. Leveraging this insight, we propose a new class of methods that achieve state-of-the-art resistance to relearning attacks.

cs.LG↗

arXiv2025

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

"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.

cs.LG↗

arXiv2025

Leveraging Per-Instance Privacy for Machine Unlearning

We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearning (Chien et al., 2024), obtaining a better utility-unlearning tradeoff by replacing worst-case privacy loss bounds with per-instance privacy losses (Thudi et al., 2024), each of which bounds the (Renyi) divergence to retraining without an individual data point. To demonstrate the practical applicability of our theory, we present empirical results showing that our theoretical predictions are born out both for Stochastic Gradient Langevin Dynamics (SGLD) as well as for standard fine-tuning without explicit noise. We further demonstrate that per-instance privacy losses correlate well with several existing data difficulty metrics, while also identifying harder groups of data points, and introduce novel evaluation methods based on loss barriers. All together, our findings provide a foundation for more efficient and adaptive unlearning strategies tailored to the unique properties of individual data points.

cs.LG↗

arXiv2024

Improved Localized Machine Unlearning Through the Lens of Memorization

Machine unlearning refers to removing the influence of a specified subset of training data from a machine learning model, efficiently, after it has already been trained. This is important for key applications, including making the model more accurate by removing outdated, mislabeled, or poisoned data. In this work, we study localized unlearning, where the unlearning algorithm operates on a (small) identified subset of parameters. Drawing inspiration from the memorization literature, we propose an improved localization strategy that yields strong results when paired with existing unlearning algorithms. We also propose a new unlearning algorithm, Deletion by Example Localization (DEL), that resets the parameters deemed-to-be most critical according to our localization strategy, and then finetunes them. Our extensive experiments on different datasets, forget sets and metrics reveal that DEL sets a new state-of-the-art for unlearning metrics, against both localized and full-parameter methods, while modifying a small subset of parameters, and outperforms the state-of-the-art localized unlearning in terms of test accuracy too.

cs.LG↗

arXiv2024

What makes unlearning hard and what to do about it

Machine unlearning is the problem of removing the effect of a subset of training data (the ''forget set'') from a trained model without damaging the model's utility e.g. to comply with users' requests to delete their data, or remove mislabeled, poisoned or otherwise problematic data. With unlearning research still being at its infancy, many fundamental open questions exist: Are there interpretable characteristics of forget sets that substantially affect the difficulty of the problem? How do these characteristics affect different state-of-the-art algorithms? With this paper, we present the first investigation aiming to answer these questions. We identify two key factors affecting unlearning difficulty and the performance of unlearning algorithms. Evaluation on forget sets that isolate these identified factors reveals previously-unknown behaviours of state-of-the-art algorithms that don't materialize on random forget sets. Based on our insights, we develop a framework coined Refined-Unlearning Meta-algorithm (RUM) that encompasses: (i) refining the forget set into homogenized subsets, according to different characteristics; and (ii) a meta-algorithm that employs existing algorithms to unlearn each subset and finally delivers a model that has unlearned the overall forget set. We find that RUM substantially improves top-performing unlearning algorithms. Overall, we view our work as an important step in (i) deepening our scientific understanding of unlearning and (ii) revealing new pathways to improving the state-of-the-art.

cs.LG↗

arXiv2024

UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with exact unlearning. More recently unlearning is often discussed as an approach for removal of impermissible knowledge i.e. knowledge that the model should not possess such as unlicensed copyrighted, inaccurate, or malicious information. The promise is that if the model does not have a certain malicious capability, then it cannot be used for the associated malicious purpose. In this paper we revisit the paradigm in which unlearning is used for in Large Language Models (LLMs) and highlight an underlying inconsistency arising from in-context learning. Unlearning can be an effective control mechanism for the training phase, yet it does not prevent the model from performing an impermissible act during inference. We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context, effectively rendering the model capable of behaving as if it knows the forgotten knowledge. As a result, we argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation. We discuss feasibility of ununlearning for modern LLMs and examine broader implications.

cs.LG↗

arXiv2024

Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition

We present the findings of the first NeurIPS competition on unlearning, which sought to stimulate the development of novel algorithms and initiate discussions on formal and robust evaluation methodologies. The competition was highly successful: nearly 1,200 teams from across the world participated, and a wealth of novel, imaginative solutions with different characteristics were contributed. In this paper, we analyze top solutions and delve into discussions on benchmarking unlearning, which itself is a research problem. The evaluation methodology we developed for the competition measures forgetting quality according to a formal notion of unlearning, while incorporating model utility for a holistic evaluation. We analyze the effectiveness of different instantiations of this evaluation framework vis-a-vis the associated compute cost, and discuss implications for standardizing evaluation. We find that the ranking of leading methods remains stable under several variations of this framework, pointing to avenues for reducing the cost of evaluation. Overall, our findings indicate progress in unlearning, with top-performing competition entries surpassing existing algorithms under our evaluation framework. We analyze trade-offs made by different algorithms and strengths or weaknesses in terms of generalizability to new datasets, paving the way for advancing both benchmarking and algorithm development in this important area.

cs.LG↗

arXiv2024

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.

cs.LG↗

arXiv2024

Data Selection for Transfer Unlearning

As deep learning models are becoming larger and data-hungrier, there are growing ethical, legal and technical concerns over use of data: in practice, agreements on data use may change over time, rendering previously-used training data impermissible for training purposes. These issues have driven increased attention to machine unlearning: removing "the influence of" a subset of training data from a trained model. In this work, we advocate for a relaxed definition of unlearning that does not address privacy applications but targets a scenario where a data owner withdraws permission of use of their data for training purposes. In this context, we consider the important problem of \emph{transfer unlearning} where a pretrained model is transferred to a target dataset that contains some "non-static" data that may need to be unlearned in the future. We propose a new method that uses a mechanism for selecting relevant examples from an auxiliary "static" dataset, and finetunes on the selected data instead of "non-static" target data; addressing all unlearning requests ahead of time. We also adapt a recent relaxed definition of unlearning to our problem setting and demonstrate that our approach is an exact transfer unlearner according to it, while being highly efficient (amortized). We find that our method outperforms the gold standard "exact unlearning" (finetuning on only the "static" portion of the target dataset) on several datasets, especially for small "static" sets, sometimes approaching an upper bound for test accuracy. We also analyze factors influencing the accuracy boost obtained by data selection.

cs.LG↗

arXiv2024

Leveraging tropical reef, bird and unrelated sounds for superior transfer learning in marine bioacoustics

Machine learning has the potential to revolutionize passive acoustic monitoring (PAM) for ecological assessments. However, high annotation and compute costs limit the field's efficacy. Generalizable pretrained networks can overcome these costs, but high-quality pretraining requires vast annotated libraries, limiting its current applicability primarily to bird taxa. Here, we identify the optimum pretraining strategy for a data-deficient domain using coral reef bioacoustics. We assemble ReefSet, a large annotated library of reef sounds, though modest compared to bird libraries at 2% of the sample count. Through testing few-shot transfer learning performance, we observe that pretraining on bird audio provides notably superior generalizability compared to pretraining on ReefSet or unrelated audio alone. However, our key findings show that cross-domain mixing which leverages bird, reef and unrelated audio during pretraining maximizes reef generalizability. SurfPerch, our pretrained network, provides a strong foundation for automated analysis of marine PAM data with minimal annotation and compute costs.

cs.SD↗