[论文] Feature Squeezing:Detecting Adversarial Examples in Deep Neural Networks

思路:对抗样本经过feature squeeze处理后大部分增加的干扰会被消除或者减小,致使feature squeeze前后的分类结果向量(distributed vector)L1距离很大,这与正常样本经过feature squeeze后结果相反,基于这样的规律进行对抗样本的过滤。

使用的攻击手段:

1. L0攻击: CW0,JSMA

2. L2攻击:CW2

3. L正无穷:FGSM、BIM、CW正无穷

squeezer选择:

1. Bit-Depth :Numpy实现。MNIST数据库1-Bit位深,CIFAR-10&ImageNet数据集4-Bit位深

2. 局部平滑处理:Scipy实现。使用2*2滑窗,padding选用reflect

3. 非局部平滑处理:OpenCV实现。先转化为CIELAB色彩域然后分别在L、AB项上去噪,最后转化为RGB域

4. 其他可使用的方法:JPEG图像压缩[Adversarial Examples in the Physical World.];数据降维[eigenfaces]

实验结果:平滑处理对于L0攻击算法更有效,Bit-Depth对于L2和L正无穷攻击算法更有效

实验对比MagNet[a Two-Pronged Defense against Adversarial Examples]

未来工作:

1. 更好的融合不同的检测子,而不是使用max方法

2. 对FGSM和BIM效果不好是因为产生的噪声较大,而featuresqueezing对小噪声效果较好

3. 不同的检测子对于false positive 5%目标的阈值不同,目前设置同一个阈值,后期设置不用阈值

  • 2
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 1
    评论
Adversarial attacks are a major concern in the field of deep learning as they can cause misclassification and undermine the reliability of deep learning models. In recent years, researchers have proposed several techniques to improve the robustness of deep learning models against adversarial attacks. Here are some of the approaches: 1. Adversarial training: This involves generating adversarial examples during training and using them to augment the training data. This helps the model learn to be more robust to adversarial attacks. 2. Defensive distillation: This is a technique that involves training a second model to mimic the behavior of the original model. The second model is then used to make predictions, making it more difficult for an adversary to generate adversarial examples that can fool the model. 3. Feature squeezing: This involves converting the input data to a lower dimensionality, making it more difficult for an adversary to generate adversarial examples. 4. Gradient masking: This involves adding noise to the gradients during training to prevent an adversary from estimating the gradients accurately and generating adversarial examples. 5. Adversarial detection: This involves training a separate model to detect adversarial examples and reject them before they can be used to fool the main model. 6. Model compression: This involves reducing the complexity of the model, making it more difficult for an adversary to generate adversarial examples. In conclusion, improving the robustness of deep learning models against adversarial attacks is an active area of research. Researchers are continually developing new techniques and approaches to make deep learning models more resistant to adversarial attacks.

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值