We argue that conclusions drawn about relative system safety or attack method efficacy via AI red teaming are often not supported by evidence provided by attack success rate (ASR) comparisons. We show, through conceptual, theoretical, and empirical contributions, that many conclusions are founded on apples-to-oranges comparisons or low-validity measurements. Our arguments are grounded in asking a simple question: When can attack success rates be meaningfully compared? To answer this question, we draw on ideas from social science measurement theory and inferential statistics, which, taken together, provide a conceptual grounding for understanding when numerical values obtained through the quantification of system attributes can be meaningfully compared. Through this lens, we articulate conditions under which ASRs can and cannot be meaningfully compared. Using jailbreaking as a running example, we provide examples and extensive discussion of apples-to-oranges ASRcomparisons and measurement validity challenges.

In enterprise settings, organizational data is segregated, siloed and carefully protected by elaborate access control frameworks. These access control structures can completely break down if an LLM fine-tuned on the siloed data serves requests, for downstream tasks, from individuals with disparate access privileges. We propose Permissioned LLMs (PermLLM), a new class of LLMs that superimpose the organizational data access control structures on query responses they generate. We formalize abstractions underpinning the means to determine whether access control enforcement happens correctly over LLM query responses. Our formalism introduces the notion of a relevant response that can be used to prove whether a PermLLM mechanism has been implemented correctly. We also introduce a novel metric, called access advantage, to empirically evaluate the efficacy of a PermLLM mechanism. We introduce three novel PermLLM mechanisms that build on Parameter Efficient Fine-Tuning to achieve the desired access control. We furthermore present two instantiations of access advantage-(i) Domain Distinguishability Index (DDI) based on Membership Inference Attacks, and (ii) Utility Gap Index (UGI) based on LLM utility evaluation. We demonstrate the efficacy of our PermLLM mechanisms through extensive experiments on five public datasets (GPQA, RCV1, SimpleQA, WMDP, and PubMedQA), in addition to evaluating the validity of DDI and UGI metrics themselves for quantifying access control in LLMs.

Recent methods for auditing the privacy of machine learning algorithms have improved computational efficiency by simultaneously intervening on multiple training examples in a single training run. Steinke et al. prove that one-run auditing indeed lower bounds the true privacy parameter of the audited algorithm, and give impressive empirical results. Their work leaves open the question of how precisely one-run auditing can uncover the true privacy parameter of an algorithm, and how that precision depends on the audited algorithm. In this work, we characterize the maximum achievable efficacy of one-run auditing and show that the key barrier to its efficacy is interference between the observable effects of different data elements. We present new conceptual approaches to minimize this barrier, towards improving the performance of one-run auditing of real machine learning algorithms.

Dataset condensation aims to synthesize compact yet informative datasets that retain the training efficacy of full-scale data, offering substantial gains in efficiency. Recent studies reveal that the condensation process can be vulnerable to backdoor attacks, where malicious triggers are injected into the condensation dataset, manipulating model behavior during inference. While prior approaches have made progress in balancing attack success rate and clean test accuracy, they often fall short in preserving stealthiness, especially in concealing the visual artifacts of condensed data or the perturbations introduced during inference. To address this challenge, we introduce \textsc{Sneakdoor}, which enhances stealthiness without compromising attack effectiveness.

Recent research has underscored the efficacy of Graph Neural Networks (GNNs) in modeling diverse geometric structures within graph data.

Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are'bound' together to produce a new vector in the same space. VSAs support the commutativity and associativity of this binding operation, along with an inverse operation, allowing one to construct symbolic-style manipulations over real-valued vectors. Most VSAs were developed before deep learning and automatic differentiation became popular and instead focused on efficacy in hand-designed systems. In this work, we introduce the Hadamard-derived linear Binding (HLB), which is designed to have favorable computational efficiency, and efficacy in classic VSA tasks, and perform well in differentiable systems.

And, for each of them, the second (final) stripe has 44 options. It could seem that small improvements in efficacy may have only a minor effect on final network accuracy, especially considering the noisiness inherent in large-scale training. Better thanreducing themagnitude oflostweights, though, iscompletely eliminating it - by using the zeros already present in the unstructured sparse weight matrix, it may be possible to find a permutation that does notloseanymagnitude after applying theN:M constraint.

If different options were available to each group offour values, then more advantageous choices canbemade, asillustrated inFigure 1.