相关论文: Understanding Rowhammer Attacks through the Lens o…

Contextual priming, where earlier stimuli covertly bias later judgments, offers an unexplored attack surface for large language models (LLMs). We uncover a contextual priming vulnerability in which the previous response in the dialogue can…

Deception technology has proven to be a sound approach against threats to information systems. Aside from well-established honeypots, decoy elements, also known as honeytokens, are an excellent method to address various types of threats.…

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

Machine learning relies on randomness as a fundamental component in various steps such as data sampling, data augmentation, weight initialization, and optimization. Most machine learning frameworks use pseudorandom number generators as the…

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing…

With deep learning deployed in many security-sensitive areas, machine learning security is becoming progressively important. Recent studies demonstrate attackers can exploit system-level techniques exploiting the RowHammer vulnerability of…

Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant knowledge sources. It is particularly useful in chatbot…

Prompt-based approaches offer a cutting-edge solution to data privacy issues in continual learning, particularly in scenarios involving multiple data suppliers where long-term storage of private user data is prohibited. Despite delivering…

Double-fetch bugs are a special type of race condition, where an unprivileged execution thread is able to change a memory location between the time-of-check and time-of-use of a privileged execution thread. If an unprivileged attacker…

Machine Unlearning (MUL) is crucial for privacy protection and content regulation, yet recent studies reveal that traces of forgotten information persist in unlearned models, enabling adversaries to resurface removed knowledge. Existing…

Precise future human motion prediction over sub-second horizons from past observations is crucial for various safety-critical applications. To date, only a few studies have examined the vulnerability of skeleton-based neural networks to…

Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools and database systems. Compound AI systems are constructed on a layered traditional software…

To address the issue of powerful row hammer (RH) attacks, our study involved an extensive analysis of the prevalent attack patterns in the field. We discovered a strong correlation between the timing and density of the active-to-active…

Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We…

Modern large reasoning models (LRMs) exhibit impressive multi-step problem-solving via chain-of-thought (CoT) reasoning. However, this iterative thinking mechanism introduces a new vulnerability surface. We present the Deadlock Attack, a…

Modern DRAM is vulnerable to read disturbance (e.g., RowHammer and RowPress) that significantly undermines the robust operation of the system. Repeatedly opening and closing a DRAM row (RowHammer) or keeping a DRAM row open for a long…

Here, we show that current LLM unlearning methods inherently reduce models' robustness, causing them to misbehave even when a single non-adversarial forget-token is present in the retain-query. Toward understanding underlying causes, we…

Within the realm of privacy-preserving machine learning, empirical privacy defenses have been proposed as a solution to achieve satisfactory levels of training data privacy without a significant drop in model utility. Most existing defenses…

The prevalence of data scraping from social media as a means to obtain datasets has led to growing concerns regarding unauthorized use of data. Data poisoning attacks have been proposed as a bulwark against scraping, as they make data…

AI agents, powered by large language models (LLMs), have transformed human-computer interactions by enabling seamless, natural, and context-aware communication. While these advancements offer immense utility, they also inherit and amplify…