Zhuo Li

Yuhao Du, Zhuo Li, Pengyu Cheng et al.

Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content, causing unexpected negative social impacts. This vulnerability highlights the necessity for robust LLM red-teaming strategies to identify and mitigate such risks before large-scale application. To detect specific types of risks, we propose a novel red-teaming method that $\textbf{A}$ttacks LLMs with $\textbf{T}$arget $\textbf{Toxi}$c $\textbf{A}$nswers ($\textbf{Atoxia}$). Given a particular harmful answer, Atoxia generates a corresponding user query and a misleading answer opening to examine the internal defects of a given LLM. The proposed attacker is trained within a reinforcement learning scheme with the LLM outputting probability of the target answer as the reward. We verify the effectiveness of our method on various red-teaming benchmarks, such as AdvBench and HH-Harmless. The empirical results demonstrate that Atoxia can successfully detect safety risks in not only open-source models but also state-of-the-art black-box models such as GPT-4o.

Songwen Zhao, Danqing Wang, Kexun Zhang et al.

Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little supervision. Although it is increasingly adopted, are vibe coding outputs really safe to deploy in production? To answer this question, we propose SU S VI B E S, a benchmark consisting of 200 feature-request software engineering tasks from real-world open-source projects, which, when given to human programmers, led to vulnerable implementations. We evaluate multiple widely used coding agents with frontier models on this benchmark. Disturbingly, all agents perform poorly in terms of software security. Although 61% of the solutions from SWE-Agent with Claude 4 Sonnet are functionally correct, only 10.5% are secure. Further experiments demonstrate that preliminary security strategies, such as augmenting the feature request with vulnerability hints, cannot mitigate these security issues. Our findings raise serious concerns about the widespread adoption of vibe-coding, particularly in security-sensitive applications.

Jian Peng, Bo Tang, Hao Jiang et al.

Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequence increases, known as the long-term catastrophic forgetting. It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference. Inspired by the memory consolidation mechanism in mammalian brains with synaptic plasticity, we propose a confrontation mechanism in which Adversarial Neural Pruning and synaptic Consolidation (ANPyC) is used to overcome the long-term catastrophic forgetting issue. The neural pruning acts as long-term depression to prune task-irrelevant parameters, while the novel synaptic consolidation acts as long-term potentiation to strengthen task-relevant parameters. During the training, this confrontation achieves a balance in that only crucial parameters remain, and non-significant parameters are freed to learn subsequent tasks. ANPyC avoids forgetting important information and makes the model efficient to learn a large number of tasks. Specifically, the neural pruning iteratively relaxes the current task's parameter conditions to expand the common parameter subspace of the task; the synaptic consolidation strategy, which consists of a structure-aware parameter-importance measurement and an element-wise parameter updating strategy, decreases the cumulative error when learning new tasks. The full source code is available at https://github.com/GeoX-Lab/ANPyC.

Zhuo Li

Capturing long-range dependency and modeling long temporal contexts is proven to benefit speaker verification tasks. In this paper, we propose the combination of the Hierarchical-Split block(HS-block) and the Depthwise Separable Self-Attention(DSSA) module to capture richer multi-range context speaker features from a local and global perspective respectively. Specifically, the HS-block splits the feature map and filters into several groups and stacks them in one block, which enlarges the receptive fields(RFs) locally. The DSSA module improves the multi-head self-attention mechanism by the depthwise-separable strategy and explicit sparse attention strategy to model the pairwise relations globally and captures effective long-range dependencies in each channel. Experiments are conducted on the Voxceleb and SITW. Our best system achieves 1.27% EER on the Voxceleb1 test set and 1.56% on SITW by applying the combination of HS-block and DSSA module.