MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs

Backdoor attacks pose a serious security threat to large language models (LLMs), which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on content-based triggers, requiring explicit modification of the input text. In this work, we show that this assumption is unnecessary and limiting. We introduce MetaBackdoor, a new class of backdoor attacks that exploits positional information as the trigger, without modifying textual content. Our key insight is that Transformer-based LLMs necessarily encode token positions to process ordered sequences. As a result, length-correlated positional structure is reflected in the model's internal computation and can be used as an effective non-content trigger signal. We demonstrate that even a simple length-based positional trigger is sufficient to activate stealthy backdoors. Unlike prior attacks, MetaBackdoor operates on visibly and semantically clean inputs and enables qualitatively new capabilities. We show that a backdoored LLM can be induced to disclose sensitive internal information, including proprietary system prompts, once a length condition is satisfied. We further demonstrate a self-activation scenario, where normal multi-turn interaction can move the conversation context into the trigger region and induce malicious tool-call behavior without attacker-supplied trigger text. In addition, MetaBackdoor is orthogonal to content-based backdoors and can be composed with them to create more precise and harder-to-detect activation conditions. Our results expand the threat model of LLM backdoors by revealing positional encoding as a previously overlooked attack surface. This challenges defenses that focus on detecting suspicious text and highlights the need for new defense strategies that explicitly account for positional triggers in modern LLM architectures.

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is explicitly stored and re-supplied. We challenge this assumption by introducing implicit memory-the ability of a model to carry state across otherwise independent interactions by encoding information in its own outputs and later recovering it when those outputs are reintroduced as input. This mechanism does not require any explicit memory module, yet it creates a persistent information channel across inference requests. As a concrete demonstration, we introduce a new class of temporal backdoors, which we call time bombs. Unlike conventional backdoors that activate on a single trigger input, time bombs activate only after a sequence of interactions satisfies hidden conditions accumulated via implicit memory. We show that such behavior can be induced today through straightforward prompting or fine-tuning. Beyond this case study, we analyze broader implications of implicit memory, including covert inter-agent communication, benchmark contamination, targeted manipulation, and training-data poisoning. Finally, we discuss detection challenges and outline directions for stress-testing and evaluation, with the goal of anticipating and controlling future developments. To promote future research, we release code and data at: https://github.com/microsoft/implicitMemory.

Design Patterns for Securing LLM Agents against Prompt Injections

As AI agents powered by Large Language Models (LLMs) become increasingly versatile and capable of addressing a broad spectrum of tasks, ensuring their security has become a critical challenge. Among the most pressing threats are prompt injection attacks, which exploit the agent's resilience on natural language inputs -- an especially dangerous threat when agents are granted tool access or handle sensitive information. In this work, we propose a set of principled design patterns for building AI agents with provable resistance to prompt injection. We systematically analyze these patterns, discuss their trade-offs in terms of utility and security, and illustrate their real-world applicability through a series of case studies.

LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge

Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous defense proposals, the systematic evaluation against adaptive adversaries remains limited, even when successful attacks can have wide security and privacy implications, and many real-world LLM-based applications remain vulnerable. We present the results of LLMail-Inject, a public challenge simulating a realistic scenario in which participants adaptively attempted to inject malicious instructions into emails in order to trigger unauthorized tool calls in an LLM-based email assistant. The challenge spanned multiple defense strategies, LLM architectures, and retrieval configurations, resulting in a dataset of 208,095 unique attack submissions from 839 participants. We release the challenge code, the full dataset of submissions, and our analysis demonstrating how this data can provide new insights into the instruction-data separation problem. We hope this will serve as a foundation for future research towards practical structural solutions to prompt injection.

Securing AI Agents with Information-Flow Control

As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees for AI agents. We present a formal model to reason about the security and expressiveness of agent planners. Using this model, we characterize the class of properties enforceable by dynamic taint-tracking and construct a taxonomy of tasks to evaluate security and utility trade-offs of planner designs. Informed by this exploration, we present Fides, a planner that tracks confidentiality and integrity labels, deterministically enforces security policies, and introduces novel primitives for selectively hiding information. Its evaluation in AgentDojo demonstrates that this approach broadens the range of tasks that can be securely accomplished. A tutorial to walk readers through the the concepts introduced in the paper can be found at https://github.com/microsoft/fides

ExclaveFL: Providing Transparency to Federated Learning using Exclaves

In federated learning (FL), data providers jointly train a model without disclosing their training data. Despite its privacy benefits, a malicious data provider can simply deviate from the correct training protocol without being detected, thus attacking the trained model. While current solutions have explored the use of trusted execution environment (TEEs) to combat such attacks, there is a mismatch with the security needs of FL: TEEs offer confidentiality guarantees, which are unnecessary for FL and make them vulnerable to side-channel attacks, and focus on coarse-grained attestation, which does not capture the execution of FL training. We describe ExclaveFL, an FL platform that achieves end-to-end transparency and integrity for detecting attacks. ExclaveFL achieves this by employing a new hardware security abstraction, exclaves, which focus on integrity-only guarantees. ExclaveFL uses exclaves to protect the execution of FL tasks, while generating signed statements containing fine-grained, hardware-based attestation reports of task execution at runtime. ExclaveFL then enables auditing using these statements to construct an attested dataflow graph and then check that the FL training jobs satisfies claims, such as the absence of attacks. Our experiments show that ExclaveFL introduces a less than 9% overhead while detecting a wide-range of attacks.

Permissive Information-Flow Analysis for Large Language Models

Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from one component can change the model's behavior and compromise the entire system, including coercing the model to spread confidential data to untrusted components. One promising approach is to tackle this problem at the system level via dynamic information flow (aka taint) tracking. Unfortunately, the traditional approach of propagating the most restrictive input label to the output is too conservative for applications where LLMs operate on inputs retrieved from diverse sources. In this paper, we propose a novel, more permissive approach to propagate information flow labels through LLM queries. The key idea behind our approach is to propagate only the labels of the samples that were influential in generating the model output and to eliminate the labels of unnecessary input. We implement and investigate the effectiveness of two variations of this approach, based on (i) prompt-based retrieval augmentation, and (ii) a $k$-nearest-neighbors language model. We compare these with the baseline of an introspection-based influence estimator that directly asks the language model to predict the output label. The results obtained highlight the superiority of our prompt-based label propagator, which improves the label in more than 85% of the cases in an LLM agent setting. These findings underscore the practicality of permissive label propagation for retrieval augmentation.

Are you still on track!? Catching LLM Task Drift with Activations

Large Language Models (LLMs) are routinely used in retrieval-augmented applications to orchestrate tasks and process inputs from users and other sources. These inputs, even in a single LLM interaction, can come from a variety of sources, of varying trustworthiness and provenance. This opens the door to prompt injection attacks, where the LLM receives and acts upon instructions from supposedly data-only sources, thus deviating from the user's original instructions. We define this as task drift, and we propose to catch it by scanning and analyzing the LLM's activations. We compare the LLM's activations before and after processing the external input in order to detect whether this input caused instruction drift. We develop two probing methods and find that simply using a linear classifier can detect drift with near perfect ROC AUC on an out-of-distribution test set. We show that this approach generalizes surprisingly well to unseen task domains, such as prompt injections, jailbreaks, and malicious instructions, without being trained on any of these attacks. Our setup does not require any modification of the LLM (e.g., fine-tuning) or any text generation, thus maximizing deployability and cost efficiency and avoiding reliance on unreliable model output. To foster future research on activation-based task inspection, decoding, and interpretability, we will release our large-scale TaskTracker toolkit, comprising a dataset of over 500K instances, representations from 4 SoTA language models, and inspection tools.

Closed-Form Bounds for DP-SGD against Record-level Inference

Machine learning models trained with differentially-private (DP) algorithms such as DP-SGD enjoy resilience against a wide range of privacy attacks. Although it is possible to derive bounds for some attacks based solely on an $(\varepsilon,\delta)$-DP guarantee, meaningful bounds require a small enough privacy budget (i.e., injecting a large amount of noise), which results in a large loss in utility. This paper presents a new approach to evaluate the privacy of machine learning models against specific record-level threats, such as membership and attribute inference, without the indirection through DP. We focus on the popular DP-SGD algorithm, and derive simple closed-form bounds. Our proofs model DP-SGD as an information theoretic channel whose inputs are the secrets that an attacker wants to infer (e.g., membership of a data record) and whose outputs are the intermediate model parameters produced by iterative optimization. We obtain bounds for membership inference that match state-of-the-art techniques, whilst being orders of magnitude faster to compute. Additionally, we present a novel data-dependent bound against attribute inference. Our results provide a direct, interpretable, and practical way to evaluate the privacy of trained models against specific inference threats without sacrificing utility.

Maatphor: Automated Variant Analysis for Prompt Injection Attacks

Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injection techniques is to add additional guardrails to the system (e.g., by updating the system prompt or using classifiers on the input and/or output of the model.) However, in the same way that variants of a piece of malware are created to evade anti-virus software, variants of a prompt injection can be created to evade the LLM's guardrails. Ideally, when a new prompt injection technique is discovered, candidate defenses should be tested not only against the successful prompt injection, but also against possible variants. In this work, we present, a tool to assist defenders in performing automated variant analysis of known prompt injection attacks. This involves solving two main challenges: (1) automatically generating variants of a given prompt according, and (2) automatically determining whether a variant was effective based only on the output of the model. This tool can also assist in generating datasets for jailbreak and prompt injection attacks, thus overcoming the scarcity of data in this domain. We evaluate Maatphor on three different types of prompt injection tasks. Starting from an ineffective (0%) seed prompt, Maatphor consistently generates variants that are at least 60% effective within the first 40 iterations.