Searcharxiv⌕ Search

arXiv subjects

Leo Schwinn

Publications and source records attributed to Leo Schwinn.

At least 19 recordsLinked to original sources
arXiv2026

Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs

Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data. We argue this not only risks reinforcing exposure to sensitive data, but also fundamentally contradicts the principle of minimizing its use. As a remedy, we propose a novel unlearning method-Partial Model Collapse (PMC), which does not require unlearning targets in the unlearning objective. Our approach is inspired by recent observations that training generative models on their own generations leads to distribution collapse, effectively removing information from model outputs. Our central insight is that model collapse can be leveraged for machine unlearning by deliberately triggering it for data we aim to remove. We theoretically analyze that our approach converges to the desired outcome, i.e. the model unlearns the data targeted for removal. We empirically demonstrate that PMC overcomes four key limitations of existing unlearning methods that explicitly optimize on unlearning targets, and more effectively removes private information from model outputs while preserving general model utility. Overall, our contributions represent an important step toward more comprehensive unlearning that better aligns with real-world privacy constraints. Code available at https://www.cs.cit.tum.de/daml/partial-model-collapse/.

cs.LG↗
arXiv2026

Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs

Accurately evaluating adversarial robustness is a longstanding challenge. A flawed attack design can inflate robustness estimates, making deployment risk assessment and defense comparison unreliable. Historically, standardized attacks such as AutoAttack have largely resolved this for image classifiers, providing a reliable evaluation baseline for systematic comparison across defenses. However, no equivalent exists for LLM jailbreak evaluation yet, where designing such an attack is considerably more difficult. A reliable attack must, among other things, be black-box compatible, applicable to arbitrary defense pipelines, and efficient, which no existing method jointly satisfies. We introduce Indirect Harm Optimization (IHO), a masked diffusion language model attacker trained via iterative preference optimization against a harmfulness judge, requiring only black-box access to the target. The same method can be used without modification as a strong adaptive attack on individual behaviors, or as an efficient amortized policy that transfers to held-out behaviors and unseen target models without fine-tuning. Even against layered defenses, such as a Circuit Breaker-trained model combined with an auxiliary detector, IHO improves attack success considerably over state-of-the-art approaches, without any defense-specific adaptation. Our results position IHO as a practical step toward the kind of standardized jailbreak evaluation that has improved reliability in the past. Code and models are available on GitHub and Hugging Face.

cs.CR↗
arXiv2026

Byte Pair Encoding for Efficient Time Series Forecasting

Existing time series tokenization methods predominantly encode a constant number of samples into individual tokens. This inflexible approach can generate excessive tokens for even simple patterns like extended constant values, resulting in substantial computational overhead. Inspired by the success of byte pair encoding, we propose the first pattern-centric tokenization scheme for time series analysis. Based on a discrete vocabulary of frequent motifs, our method merges samples with underlying patterns into tokens, compressing time series adaptively. Exploiting our finite set of motifs and the continuous properties of time series, we further introduce conditional decoding as a lightweight yet powerful post-hoc optimization method, which requires no gradient computation and adds no computational overhead. On recent time series foundation models, our motif-based tokenization improves forecasting performance by 40% and boosts efficiency by 2314% on average. Conditional decoding further reduces MSE by up to 48%. In an extensive analysis, we demonstrate the adaptiveness of our tokenization to diverse temporal patterns, its generalization to unseen data, and its meaningful token representations capturing distinct time series properties, including statistical moments and trends.

cs.LG↗
arXiv2026

LLM-Safety Evaluations Lack Robustness

In this paper, we argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise, such as small datasets, methodological inconsistencies, and unreliable evaluation setups. This can, at times, make it impossible to evaluate and compare attacks and defenses fairly, thereby slowing progress. We systematically analyze the LLM safety evaluation pipeline, covering dataset curation, optimization strategies for automated red-teaming, response generation, and response evaluation using LLM judges. At each stage, we identify key issues and highlight their practical impact. We also propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers. Lastly, we offer an opposing perspective, highlighting practical reasons for existing limitations. We believe that addressing the outlined problems in future research will improve the field's ability to generate easily comparable results and make measurable progress.

cs.CR↗
arXiv2026

Joint Relational Database Generation via Graph-Conditional Diffusion Models

Building generative models for relational databases (RDBs) is important for many applications, such as privacy-preserving data release and augmenting real datasets. However, most prior works either focus on single-table generation or adapt single-table models to the multi-table setting by relying on autoregressive factorizations and sequential generation. These approaches limit parallelism, restrict flexibility in downstream applications, and compound errors due to commonly made conditional independence assumptions. In this paper, we propose a fundamentally different approach: jointly modeling all tables in an RDB without imposing any table order. By using a natural graph representation of RDBs, we propose the Graph-Conditional Relational Diffusion Model (GRDM), which leverages a graph neural network to jointly denoise row attributes and capture complex inter-table dependencies. Extensive experiments on six real-world RDBs demonstrate that our approach substantially outperforms autoregressive baselines in modeling multi-hop inter-table correlations and achieves state-of-the-art performance on single-table fidelity metrics. Our code is available at https://github.com/ketatam/rdb-diffusion.

cs.LG↗
arXiv2026

A Scalable Multi-Task Model for Virtual Sensors

Virtual sensors replace expensive physical sensors in critical applications through machine learning by predicting target signals from available measurements. Existing virtual sensor approaches require application-specific models with hand-selected inputs for each sensor, cannot leverage task synergies, and lack consistent benchmarks. While emerging time series foundation models offer general-purpose, pretrained solutions in other domains, they are computationally expensive and limited to predicting their input signals, making them incompatible with virtual sensors. We introduce the first multi-task model for virtual sensors addressing both limitations. Our unified model can simultaneously predict diverse virtual sensors exploiting synergies while maintaining computational efficiency. It learns relevant input signals for each virtual sensor, eliminating expert knowledge requirements while adding explainability. In our large-scale evaluation on three standard benchmarks and an application-specific dataset with over 18 billion samples, our architecture reduces computation time by up to 415x and memory requirements by 951x, while maintaining or even improving predictive quality compared to unified baselines. Compared to existing isolated models for a single virtual sensor, our unified approach generates superior predictions at similar inference speed while scaling gracefully to hundreds of virtual sensors with nearly constant parameter count, enabling practical deployment in large-scale sensor networks.

cs.LG↗
arXiv2026

Adversarial Robustness of Graph Transformers

Existing studies have shown that Message-Passing Graph Neural Networks (MPNNs) are highly susceptible to adversarial attacks. In contrast, despite the increasing importance of Graph Transformers (GTs), their robustness properties are unexplored. We close this gap and design the first adaptive attacks for GTs. In particular, we provide general design principles for strong gradient-based attacks on GTs w.r.t. structure perturbations and instantiate our attack framework for five representative and popular GT architectures. Specifically, we study GTs with specialized attention mechanisms and Positional Encodings (PEs) based on pairwise shortest paths, random walks, and the Laplacian spectrum. We evaluate our attacks on multiple tasks and perturbation models, including structure perturbations for node and graph classification, and node injection for graph classification. Our results reveal that GTs can be catastrophically fragile in many cases. Addressing this vulnerability, we show how our adaptive attacks can be effectively used for adversarial training, substantially improving robustness.

cs.LG↗
arXiv2026

A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Automated \enquote{LLM-as-a-Judge} frameworks have become the de facto standard for scalable evaluation across natural language processing. For instance, in safety evaluation, these judges are relied upon to evaluate harmfulness in order to benchmark the robustness of safety against adversarial attacks. However, we show that existing validation protocols fail to account for substantial distribution shifts inherent to red-teaming: diverse victim models exhibit distinct generation styles, attacks distort output patterns, and semantic ambiguity varies significantly across jailbreak scenarios. Through a comprehensive audit using 6642 human-verified labels, we reveal that the unpredictable interaction of these shifts often causes judge performance to degrade to near random chance. This stands in stark contrast to the high human agreement reported in prior work. Crucially, we find that many attacks inflate their success rates by exploiting judge insufficiencies rather than eliciting genuinely harmful content. To enable more reliable evaluation, we propose ReliableBench, a benchmark of behaviors that remain more consistently judgeable, and JudgeStressTest, a dataset designed to expose judge failures. Data available at: https://github.com/SchwinnL/LLMJudgeReliability.

cs.CL↗
arXiv2026

Sampling-aware Adversarial Attacks Against Large Language Models

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy generations, overlooking the inherently stochastic nature of LLMs and overestimating robustness. We show that for the goal of eliciting harmful responses, repeated sampling of model outputs during the attack complements prompt optimization and serves as a strong and efficient attack vector. By casting attacks as a resource allocation problem between optimization and sampling, we empirically determine compute-optimal trade-offs and show that integrating sampling into existing attacks boosts success rates by up to 37\% and improves efficiency by up to two orders of magnitude. We further analyze how distributions of output harmfulness evolve during an adversarial attack, discovering that many common optimization strategies have little effect on output harmfulness. Finally, we introduce a label-free proof-of-concept objective based on entropy maximization, demonstrating how our sampling-aware perspective enables new optimization targets. Overall, our findings establish the importance of sampling in attacks to accurately assess and strengthen LLM safety at scale.

cs.LG↗
arXiv2026

Closing the Distribution Gap in Adversarial Training for LLMs

Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant progress, models remain vulnerable to simple in-distribution exploits, such as rewriting prompts in the past tense or translating them into other languages. We argue that this persistent fragility stems from a fundamental limitation in current adversarial training algorithms: they minimize adversarial loss on their training set but inadequately cover the data distribution, resulting in vulnerability to seemingly simple attacks. To bridge this gap, we propose Distributional Adversarial Training, DAT. We leverage Diffusion LLMs to approximate the true joint distribution of prompts and responses, enabling generation of diverse, high-likelihood samples that address generalization failures. By combining optimization over the data distribution provided by the diffusion model with continuous adversarial training, DAT achieves substantially higher adversarial robustness than previous methods.

cs.LG↗
arXiv2025

Unexplored flaws in multiple-choice VQA make benchmarking unreliable

Previous works identify sensitivity to option order as a key issue in multiple-choice VQA (MC-VQA) evaluation and propose protocols to mitigate this effect. We show that such mitigation is insufficient to ensure the validity of MC-VQA as a reliable benchmark for Multimodal Large Language Model (MLLMs): performance remains highly sensitive to semantically neutral prompt format choices that are not controlled by current benchmarks. In a large-scale study spanning seven MLLMs and five MC-VQAs datasets, we find frequent rank reversals even under order-invariant evaluation. These reversals arise when we systematically vary option ID sets, delimiters, and separators, yielding 48 semantically equivalent prompt formats. Mechanistic analyses trace this instability to low-level language modeling effects: tokenizer-induced fusion or removal of option ID tokens introduces corrupted option ID tokens into the input sequence, while the choice of option ID sets directly affects the reliability of attention patterns for option selection. Accordingly, MC-VQA rankings correlate weakly with open-ended evaluation, indicating that MC-VQA reflects option-selection dynamics in addition to multimodal reasoning. These findings identify prompt formatting as a major, previously under-controlled confounder in MC-VQA benchmarking and motivate evaluation protocols that explicitly control prompt format sensitivity.

cs.CV↗
arXiv2025

AdversariaLLM: A Unified and Modular Toolbox for LLM Robustness Research

The rapid expansion of research on Large Language Model (LLM) safety and robustness has produced a fragmented and oftentimes buggy ecosystem of implementations, datasets, and evaluation methods. This fragmentation makes reproducibility and comparability across studies challenging, hindering meaningful progress. To address these issues, we introduce AdversariaLLM, a toolbox for conducting LLM jailbreak robustness research. Its design centers on reproducibility, correctness, and extensibility. The framework implements twelve adversarial attack algorithms, integrates seven benchmark datasets spanning harmfulness, over-refusal, and utility evaluation, and provides access to a wide range of open-weight LLMs via Hugging Face. The implementation includes advanced features for comparability and reproducibility such as compute-resource tracking, deterministic results, and distributional evaluation techniques. \name also integrates judging through the companion package JudgeZoo, which can also be used independently. Together, these components aim to establish a robust foundation for transparent, comparable, and reproducible research in LLM safety.

cs.AI↗
arXiv2025

Diffusion LLMs are Natural Adversaries for any LLM

We introduce a novel framework that transforms the resource-intensive (adversarial) prompt optimization problem into an \emph{efficient, amortized inference task}. Our core insight is that pretrained, non-autoregressive generative LLMs, such as Diffusion LLMs, which model the joint distribution over prompt-response pairs, can serve as powerful surrogates for prompt search. This approach enables the direct conditional generation of prompts, effectively replacing costly, per-instance discrete optimization with a small number of parallelizable samples. We provide a probabilistic analysis demonstrating that under mild fidelity assumptions, only a few conditional samples are required to recover high-reward (harmful) prompts. Empirically, we find that the generated prompts are low-perplexity, diverse jailbreaks that exhibit strong transferability to a wide range of black-box target models, including robustly trained and proprietary LLMs. Beyond adversarial prompting, our framework opens new directions for red teaming, automated prompt optimization, and leveraging emerging Flow- and Diffusion-based LLMs.

cs.LG↗
arXiv2025

FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering

While Multimodal Large Language Models (MLLMs) offer strong perception and reasoning capabilities for image-text input, Visual Question Answering (VQA) focusing on small image details still remains a challenge. Although visual cropping techniques seem promising, recent approaches have several limitations: the need for task-specific fine-tuning, low efficiency due to uninformed exhaustive search, or incompatibility with efficient attention implementations. We address these shortcomings by proposing a training-free visual cropping method, dubbed FOCUS, that leverages MLLM-internal representations to guide the search for the most relevant image region. This is accomplished in four steps: first, we identify the target object(s) in the VQA prompt; second, we compute an object relevance map using the key-value (KV) cache; third, we propose and rank relevant image regions based on the map; and finally, we perform the fine-grained VQA task using the top-ranked region. As a result of this informed search strategy, FOCUS achieves strong performance across four fine-grained VQA datasets and three types of MLLMs. It outperforms three popular visual cropping methods in both accuracy and efficiency, and matches the best-performing baseline, ZoomEye, while requiring 3 - 6.5 x less compute.

cs.CV↗
arXiv2025

A Unified Approach Towards Active Learning and Out-of-Distribution Detection

When applying deep learning models in open-world scenarios, active learning (AL) strategies are crucial for identifying label candidates from a nearly infinite amount of unlabeled data. In this context, robust out-of-distribution (OOD) detection mechanisms are essential for handling data outside the target distribution of the application. However, current works investigate both problems separately. In this work, we introduce SISOM as the first unified solution for both AL and OOD detection. By leveraging feature space distance metrics SISOM combines the strengths of the currently independent tasks to solve both effectively. We conduct extensive experiments showing the problems arising when migrating between both tasks. In these evaluations SISOM underlined its effectiveness by achieving first place in two of the widely used OpenOOD benchmarks and second place in the remaining one. In AL, SISOM outperforms others and delivers top-1 performance in three benchmarks

cs.CV↗
arXiv2025

A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens

Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such distribution shifts are often brittle and degrade performance on desirable tasks. To address these pitfalls, we propose augmenting the model's vocabulary with a special red flag token, and training the model to insert this token whenever harmful content is generated or imminent. This approach enables the model to explicitly learn the concept of harmfulness in its representations, with minimal impact on utility due to the marginal change in the generated distribution of natural language. Moreover, because the token is embedded in the model's vocabulary, we can naturally leverage the LLMs' generalization capabilities, such as in-context learning (ICL) and out-of-distribution generalization to languages that are not formally supported (e.g., Japanese for Llama3). In particular, we demonstrate that through ICL alone, the model can learn to initiate reflective reasoning upon generating the red flag token at inference, which steers the response away from harmful continuations or enables self-correction when the flag is raised falsely. This approach is orthogonal and complementary to existing safety technique (such as safety classifiers or standard safety training) and easier to evaluate in comparison to natural language refusals, as it does not require a human or automated judge to assess the harmlessness of the answers.

cs.CL↗
arXiv2025

Efficient Time Series Processing for Transformers and State-Space Models through Token Merging

Despite recent advances in subquadratic attention mechanisms or state-space models, processing long token sequences still imposes significant computational requirements. Token merging has emerged as a solution to increase computational efficiency in computer vision architectures. In this work, we perform the first investigations of token merging in time series analysis on both transformers and state-space models. We further introduce local merging, a domain-specific token merging algorithm that selectively combines tokens within a local neighborhood, achieving two major benefits: a) Local merging can adjust its computational complexity from quadratic to linear based on the neighborhood size to effectively scale to long sequences; b) Local merging is the first causal merging scheme enabling token merging in transformer decoders. Further, we identify spectral properties of the input data that reliably predict the potential benefits of local merging without requiring evaluation on downstream tasks. Our comprehensive empirical evaluation demonstrates that local merging offers substantial efficiency gains with minimal impact on accuracy, achieving up to 5400% acceleration on the recently proposed Chronos foundation model.

cs.LG↗
arXiv2025

Investigating the Robustness of Retrieval-Augmented Generation at the Query Level

Large language models (LLMs) are very costly and inefficient to update with new information. To address this limitation, retrieval-augmented generation (RAG) has been proposed as a solution that dynamically incorporates external knowledge during inference, improving factual consistency and reducing hallucinations. Despite its promise, RAG systems face practical challenges-most notably, a strong dependence on the quality of the input query for accurate retrieval. In this paper, we investigate the sensitivity of different components in the RAG pipeline to various types of query perturbations. Our analysis reveals that the performance of commonly used retrievers can degrade significantly even under minor query variations. We study each module in isolation as well as their combined effect in an end-to-end question answering setting, using both general-domain and domain-specific datasets. Additionally, we propose an evaluation framework to systematically assess the query-level robustness of RAG pipelines and offer actionable recommendations for practitioners based on the results of more than 1092 experiments we performed.

cs.CL↗