arXiv subjects

Erik Jenner

Publications and source records attributed to Erik Jenner.

17 recordsLinked to original sources

arXiv2026

GDM AI Control Roadmap

AI agents are rapidly accelerating work at frontier AI companies, helping with AI R&D, cyber-defence, and advancing scientific discoveries. As these agents become more tightly integrated into our systems, unlocking their full potential requires rethinking how we do security. We should not assume that AI agents are always perfectly aligned, but should instead build in multiple layers of defence. We present the GDM AI Control Roadmap (v0.1) -- a first-of-its-kind blueprint for internal security against potentially misaligned AI. This report provides: * Threat modelling: We adopt a conservative approach to threat modelling and assume a hypothetical AI adversary pursuing undesirable goals in internal deployment. We introduce TRAIT&R, a taxonomy of tactics and techniques available to such a hypothetical AI adversary, building on the established security framework MITRE ATT&CK. * Capability-based mitigation: Because controlling more capable models requires more costly interventions, we link specific defensive measures to evolving model capabilities (such as the ability to reason opaquely or execute complex cyberattacks). As models get more powerful, our defences should escalate accordingly. We outline four Detection tiers (D1-D4) and three Prevention and Response tiers (R1-R3). * A portfolio of practical defences: We suggest 15 concrete, tiered mitigations. These range from low-cost interventions for current models (e.g., chain-of-thought monitoring, asynchronous alerts) to advanced safeguards for future models (e.g., real-time access control, system-level anomaly detection, internal activations monitoring, and shutdown infrastructure). AI control is a nascent field, and implementing these mitigations requires navigating difficult trade-offs between security and developer velocity. We expect the roadmap to evolve as we gain more experience and as the field in turn evolves.

cs.CR↗

arXiv2026

Frontier Models Can Take Actions at Low Probabilities

Pre-deployment evaluations inspect only a limited sample of model actions. A malicious model seeking to evade oversight could exploit this by randomizing when to "defect": misbehaving so rarely that no malicious actions are observed during evaluation, but often enough that they occur eventually in deployment. But this requires taking actions at very low rates, while maintaining calibration. Are frontier models even capable of that? We prompt the GPT-5, Claude-4.5 and Qwen-3 families to take a target action at low probabilities (e.g. 0.01%), either given directly or requiring derivation, and evaluate their calibration (i.e. whether they perform the target action roughly 1 in 10,000 times when resampling). We find that frontier models are surprisingly good at this task. If there is a source of entropy in-context (such as a UUID), they maintain high calibration at rates lower than 1 in 100,000 actions. Without external entropy, some models can still reach rates lower than 1 in 10,000. When target rates are given, larger models achieve good calibration at lower rates. Yet, when models must derive the optimal target rate themselves, all models fail to achieve calibration without entropy or hint to generate it. Successful low-rate strategies require explicit Chain-of-Thought (CoT) reasoning, so malicious models attempting this approach could currently be caught by a CoT monitor. However, scaling trends suggest future evaluations may be unable to rely on models' lack of target rate calibration, especially if CoT is no longer legible.

cs.LG↗

arXiv2025

Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability

Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignment monitoring: when models articulate their reasoning faithfully, monitors can detect and mitigate harmful behaviors before undesirable outcomes occur. However, a key uncertainty is: Can models obfuscate their CoT in order to pursue hidden adversarial objectives while evading detection? To answer this question and thus stress-test CoT monitorability, we develop a composable and quantifiable taxonomy of prompts to elicit CoT obfuscation. We evaluate both internal CoT (reasoning traces) and external CoT (prompted reasoning in outputs) using toy tasks and more realistic environments in SHADE-Arena. We show that: (i) CoT monitoring performs accurately and efficiently without obfuscation pressure. (ii) Under strong obfuscation pressure, some models successfully complete adversarial tasks while evading detection. (iii) Models do not obfuscate their internal CoT as much as their external CoT (under prompt pressure). These results suggest that while CoT provides valuable oversight in benign settings, robust deployment requires model-specific stress-testing of monitorability.

cs.CR↗

arXiv2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

cs.AI↗

arXiv2025

When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors

While chain-of-thought (CoT) monitoring is an appealing AI safety defense, recent work on "unfaithfulness" has cast doubt on its reliability. These findings highlight an important failure mode, particularly when CoT acts as a post-hoc rationalization in applications like auditing for bias. However, for the distinct problem of runtime monitoring to prevent severe harm, we argue the key property is not faithfulness but monitorability. To this end, we introduce a conceptual framework distinguishing CoT-as-rationalization from CoT-as-computation. We expect that certain classes of severe harm will require complex, multi-step reasoning that necessitates CoT-as-computation. Replicating the experimental setups of prior work, we increase the difficulty of the bad behavior to enforce this necessity condition; this forces the model to expose its reasoning, making it monitorable. We then present methodology guidelines to stress-test CoT monitoring against deliberate evasion. Applying these guidelines, we find that models can learn to obscure their intentions, but only when given significant help, such as detailed human-written strategies or iterative optimization against the monitor. We conclude that, while not infallible, CoT monitoring offers a substantial layer of defense that requires active protection and continued stress-testing.

cs.AI↗

arXiv2025

RL-Obfuscation: Can Language Models Learn to Evade Latent-Space Monitors?

Latent-space monitors aim to detect undesirable behaviours in Large Language Models by leveraging their internal representations rather than relying solely on black-box outputs. These methods have shown promise in identifying behaviours such as deception and unsafe completions. However, these monitors may themselves become training signals, for example, by using problematic samples found in deployment to retrain models. This raises an important question: can models learn to evade such monitors? To evaluate this capability, we introduce RL-Obfuscation, in which LLMs are finetuned via reinforcement learning to evade latent-space monitors while maintaining their blackbox behaviour. We apply RL-Obfuscation to Language Models ranging from 7B to 14B parameters and evaluate their Evasion Success Rate against a suite of monitors. We find that token-level monitors are highly vulnerable to this attack while more holistic monitors, such as max-pooling or attention-based probes, remain robust. Moreover, for these vulnerable monitors, models trained to evade a single static monitor can generalise to evade other unseen monitors. We also find that the models can be trained to conditionally bypass latent-space monitors on only certain inputs. Finally, we study how the models bypass these monitors and find that the model can learn to repurpose tokens to have different internal representations.

cs.LG↗

arXiv2024

Obfuscated Activations Bypass LLM Latent-Space Defenses

Recent latent-space monitoring techniques have shown promise as defenses against LLM attacks. These defenses act as scanners that seek to detect harmful activations before they lead to undesirable actions. This prompts the question: Can models execute harmful behavior via inconspicuous latent states? Here, we study such obfuscated activations. We show that state-of-the-art latent-space defenses -- including sparse autoencoders, representation probing, and latent OOD detection -- are all vulnerable to obfuscated activations. For example, against probes trained to classify harmfulness, our attacks can often reduce recall from 100% to 0% while retaining a 90% jailbreaking rate. However, obfuscation has limits: we find that on a complex task (writing SQL code), obfuscation reduces model performance. Together, our results demonstrate that neural activations are highly malleable: we can reshape activation patterns in a variety of ways, often while preserving a network's behavior. This poses a fundamental challenge to latent-space defenses.

cs.LG↗

arXiv2024

Evidence of Learned Look-Ahead in a Chess-Playing Neural Network

Do neural networks learn to implement algorithms such as look-ahead or search "in the wild"? Or do they rely purely on collections of simple heuristics? We present evidence of learned look-ahead in the policy network of Leela Chess Zero, the currently strongest neural chess engine. We find that Leela internally represents future optimal moves and that these representations are crucial for its final output in certain board states. Concretely, we exploit the fact that Leela is a transformer that treats every chessboard square like a token in language models, and give three lines of evidence (1) activations on certain squares of future moves are unusually important causally; (2) we find attention heads that move important information "forward and backward in time," e.g., from squares of future moves to squares of earlier ones; and (3) we train a simple probe that can predict the optimal move 2 turns ahead with 92% accuracy (in board states where Leela finds a single best line). These findings are an existence proof of learned look-ahead in neural networks and might be a step towards a better understanding of their capabilities.

cs.LG↗

arXiv2024

Diffusion On Syntax Trees For Program Synthesis

Large language models generate code one token at a time. Their autoregressive generation process lacks the feedback of observing the program's output. Training LLMs to suggest edits directly can be challenging due to the scarcity of rich edit data. To address these problems, we propose neural diffusion models that operate on syntax trees of any context-free grammar. Similar to image diffusion models, our method also inverts ``noise'' applied to syntax trees. Rather than generating code sequentially, we iteratively edit it while preserving syntactic validity, which makes it easy to combine this neural model with search. We apply our approach to inverse graphics tasks, where our model learns to convert images into programs that produce those images. Combined with search, our model is able to write graphics programs, see the execution result, and debug them to meet the required specifications. We additionally show how our system can write graphics programs for hand-drawn sketches.

cs.AI↗

arXiv2024

Foundational Challenges in Assuring Alignment and Safety of Large Language Models

This work identifies 18 foundational challenges in assuring the alignment and safety of large language models (LLMs). These challenges are organized into three different categories: scientific understanding of LLMs, development and deployment methods, and sociotechnical challenges. Based on the identified challenges, we pose $200+$ concrete research questions.

cs.LG↗

arXiv2024

When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback

Past analyses of reinforcement learning from human feedback (RLHF) assume that the human evaluators fully observe the environment. What happens when human feedback is based only on partial observations? We formally define two failure cases: deceptive inflation and overjustification. Modeling the human as Boltzmann-rational w.r.t. a belief over trajectories, we prove conditions under which RLHF is guaranteed to result in policies that deceptively inflate their performance, overjustify their behavior to make an impression, or both. Under the new assumption that the human's partial observability is known and accounted for, we then analyze how much information the feedback process provides about the return function. We show that sometimes, the human's feedback determines the return function uniquely up to an additive constant, but in other realistic cases, there is irreducible ambiguity. We propose exploratory research directions to help tackle these challenges, experimentally validate both the theoretical concerns and potential mitigations, and caution against blindly applying RLHF in partially observable settings.

cs.LG↗

arXiv2023

STARC: A General Framework For Quantifying Differences Between Reward Functions

In order to solve a task using reinforcement learning, it is necessary to first formalise the goal of that task as a reward function. However, for many real-world tasks, it is very difficult to manually specify a reward function that never incentivises undesirable behaviour. As a result, it is increasingly popular to use reward learning algorithms, which attempt to learn a reward function from data. However, the theoretical foundations of reward learning are not yet well-developed. In particular, it is typically not known when a given reward learning algorithm with high probability will learn a reward function that is safe to optimise. This means that reward learning algorithms generally must be evaluated empirically, which is expensive, and that their failure modes are difficult to anticipate in advance. One of the roadblocks to deriving better theoretical guarantees is the lack of good methods for quantifying the difference between reward functions. In this paper we provide a solution to this problem, in the form of a class of pseudometrics on the space of all reward functions that we call STARC (STAndardised Reward Comparison) metrics. We show that STARC metrics induce both an upper and a lower bound on worst-case regret, which implies that our metrics are tight, and that any metric with the same properties must be bilipschitz equivalent to ours. Moreover, we also identify a number of issues with reward metrics proposed by earlier works. Finally, we evaluate our metrics empirically, to demonstrate their practical efficacy. STARC metrics can be used to make both theoretical and empirical analysis of reward learning algorithms both easier and more principled.

cs.LG↗

arXiv2022

imitation: Clean Imitation Learning Implementations

imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation learning algorithms and a preference comparison algorithm. The implementations have been benchmarked against previous results, and automated tests cover 98% of the code. Moreover, the algorithms are implemented in a modular fashion, making it simple to develop novel algorithms in the framework. Our source code, including documentation and examples, is available at https://github.com/HumanCompatibleAI/imitation

cs.LG↗

arXiv2022

Calculus on MDPs: Potential Shaping as a Gradient

In reinforcement learning, different reward functions can be equivalent in terms of the optimal policies they induce. A particularly well-known and important example is potential shaping, a class of functions that can be added to any reward function without changing the optimal policy set under arbitrary transition dynamics. Potential shaping is conceptually similar to potentials, conservative vector fields and gauge transformations in math and physics, but this connection has not previously been formally explored. We develop a formalism for discrete calculus on graphs that abstract a Markov Decision Process, and show how potential shaping can be formally interpreted as a gradient within this framework. This allows us to strengthen results from Ng et al. (1999) describing conditions under which potential shaping is the only additive reward transformation to always preserve optimal policies. As an additional application of our formalism, we define a rule for picking a single unique reward function from each potential shaping equivalence class.

cs.LG↗

arXiv2022

Preprocessing Reward Functions for Interpretability

In many real-world applications, the reward function is too complex to be manually specified. In such cases, reward functions must instead be learned from human feedback. Since the learned reward may fail to represent user preferences, it is important to be able to validate the learned reward function prior to deployment. One promising approach is to apply interpretability tools to the reward function to spot potential deviations from the user's intention. Existing work has applied general-purpose interpretability tools to understand learned reward functions. We propose exploiting the intrinsic structure of reward functions by first preprocessing them into simpler but equivalent reward functions, which are then visualized. We introduce a general framework for such reward preprocessing and propose concrete preprocessing algorithms. Our empirical evaluation shows that preprocessed rewards are often significantly easier to understand than the original reward.

cs.LG↗

arXiv2021

Extensions of Karger's Algorithm: Why They Fail in Theory and How They Are Useful in Practice

The minimum graph cut and minimum $s$-$t$-cut problems are important primitives in the modeling of combinatorial problems in computer science, including in computer vision and machine learning. Some of the most efficient algorithms for finding global minimum cuts are randomized algorithms based on Karger's groundbreaking contraction algorithm. Here, we study whether Karger's algorithm can be successfully generalized to other cut problems. We first prove that a wide class of natural generalizations of Karger's algorithm cannot efficiently solve the $s$-$t$-mincut or the normalized cut problem to optimality. However, we then present a simple new algorithm for seeded segmentation / graph-based semi-supervised learning that is closely based on Karger's original algorithm, showing that for these problems, extensions of Karger's algorithm can be useful. The new algorithm has linear asymptotic runtime and yields a potential that can be interpreted as the posterior probability of a sample belonging to a given seed / class. We clarify its relation to the random walker algorithm / harmonic energy minimization in terms of distributions over spanning forests. On classical problems from seeded image segmentation and graph-based semi-supervised learning on image data, the method performs at least as well as the random walker / harmonic energy minimization / Gaussian processes.

cs.DS↗

arXiv2021

Steerable Partial Differential Operators for Equivariant Neural Networks

Recent work in equivariant deep learning bears strong similarities to physics. Fields over a base space are fundamental entities in both subjects, as are equivariant maps between these fields. In deep learning, however, these maps are usually defined by convolutions with a kernel, whereas they are partial differential operators (PDOs) in physics. Developing the theory of equivariant PDOs in the context of deep learning could bring these subjects even closer together and lead to a stronger flow of ideas. In this work, we derive a $G$-steerability constraint that completely characterizes when a PDO between feature vector fields is equivariant, for arbitrary symmetry groups $G$. We then fully solve this constraint for several important groups. We use our solutions as equivariant drop-in replacements for convolutional layers and benchmark them in that role. Finally, we develop a framework for equivariant maps based on Schwartz distributions that unifies classical convolutions and differential operators and gives insight about the relation between the two.

cs.LG↗