Related papers: STARE: Step-wise Temporal Alignment and Red-teamin…

Image-text retrieval has developed rapidly in recent years. However, it is still a challenge in remote sensing due to visual-semantic imbalance, which leads to incorrect matching of non-semantic visual and textual features. To solve this…

Testing and evaluation is an important step before the large-scale application of the autonomous driving systems (ADSs). Based on the three level of scenario abstraction theory, a testing can be performed within a logical scenario, followed…

Language Model (LM) agents have demonstrated remarkable capabilities in solving tasks that require multiple interactions with the environment. However, they remain vulnerable in environments where a single error often leads to irrecoverable…

As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional…

Reinforcement learning (RL) techniques have achieved impressive performance on simulated benchmarks such as Atari100k, yet recent advances remain largely confined to simulation and show limited transfer to real-world domains. A central…

Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those containing triggers)…

While many text-to-audio systems produce monophonic or fixed-stereo outputs, generating audio with user-defined spatial properties remains a challenge. Existing deep learning-based spatialization methods often rely on latent-space…

Speculative decoding is a technique to leverage hardware concurrency in order to enable multiple steps of token generation in a single forward pass, thus improving the efficiency of large-scale autoregressive (AR) Transformer models.…

We introduce Synthetic Alignment data Generation for Safety Evaluation and Red Teaming (SAGE-RT or SAGE) a novel pipeline for generating synthetic alignment and red-teaming data. Existing methods fall short in creating nuanced and diverse…

In large-scale LLM pre-training systems with 100k+ GPUs, failures become the norm rather than the exception, and restart costs can dominate wall-clock training time. However, existing fault-tolerance mechanisms are largely unprepared for…

Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase. We introduce Eyes-on-Me, a modular attack that decomposes an…

Spiking Neural Networks (SNNs) are inherently suited for continuous learning due to their event-driven temporal dynamics; however, their application to Class-Incremental Learning (CIL) has been hindered by catastrophic forgetting and the…

Large Language Models (LLMs) are increasingly used as autonomous agents for multi-step tasks. However, most existing frameworks fail to maintain a structured understanding of the task state, often relying on linear prompt concatenation or…

Large vision-language models (VLMs) are highly vulnerable to multimodal jailbreak attacks that exploit visual-textual interactions to bypass safety guardrails. In this paper, we present DTR, a novel inference-time defense that mitigates…

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Simulation-based design space exploration (DSE) aims to efficiently optimize high-dimensional structured designs under complex constraints and expensive evaluation costs. Existing approaches, including heuristic and multi-step reinforcement…

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to…

The effectiveness of collision-free trajectory planners depends on the quality and diversity of training data, especially for rare scenarios. A widely used approach to improve dataset diversity involves generating realistic synthetic…

The proliferation of jailbreak attacks against large language models (LLMs) highlights the need for robust security measures. However, in multi-round dialogues, malicious intentions may be hidden in interactions, leading LLMs to be more…

Red teaming is critical for identifying vulnerabilities and building trust in current LLMs. However, current automated methods for Large Language Models (LLMs) rely on brittle prompt templates or single-turn attacks, failing to capture the…